Gaius

Curated research in AI reasoning, epistemic uncertainty, and normative aesthetics

MANTA: Machine Learning Augmented Tiering Advisor
arXiv:2610.00714v1 Announce Type: new Abstract: Memory tiering has been used to expand memory capacity, particularly in datacenters, by combining fast DRAM with slower tiers, including CXL-attached memory. Its effectiveness depends on keeping useful pages in the fast tier, but existing heuristic policies can lag behind changing hot sets in phased or bursty workloads. To explore these limitations,
arxiv Oct 4
The Other Half of Workflow Portability: Evidence-Backed HPC Site Profiles with Agentic Discovery
arXiv:2610.00971v1 Announce Type: new Abstract: Moving a workflow developed and tested at one HPC site to another rarely succeeds without some amount of trial and error. Package managers rebuild software environments, containers ship whole filesystems, and workflow specifications such as backpacks package a workflow with its software, data, and resource requirements. These approaches address one
arxiv Oct 4
RapidMoE: Exploiting Cross-Asymmetry via Adaptive Residual Offloading for Large-Scale MoE Inference
arXiv:2610.01265v1 Announce Type: new Abstract: The widespread adoption of Mixture-of-Experts (MoE) has created a growing need for deployment on heterogeneous platforms. However, it exposes a fundamental mismatch between the algorithmic demands of large-scale MoE and the disparate characteristics of hardware.Existing CPU-GPU hybrid inference systems fail to resolve this as they either encounter P
arxiv Oct 4
MoE-CORE: Coordinated Expert Offloading and Residency for Memory-Constrained MoE Inference
arXiv:2610.01950v1 Announce Type: new Abstract: Sparse expert activation reduces MoE models' computation, yet expert weights can exceed limited device memory. Offloading makes inference feasible on a compact AI appliance but exposes host-to-device transfers to the inference path. We present MoE-CORE, a system that coordinates expert offloading and residency for memory-constrained MoE inference. I
arxiv Oct 3
GridSMR: Causal Compression for Sharded Blockchains
arXiv:2610.01443v1 Announce Type: new Abstract: We present GridSMR, a sharded blockchain that scales execution horizontally while allowing dependent cross-shard operations to progress within a single block. Existing sharded systems typically place coordination between dependent cross-shard steps, making latency grow with causal depth. GridSMR localizes atomicity to individual accounts and execute
arxiv Oct 3
Towards a Cloud Fog Edge System for Smart Building
arXiv:2610.01647v1 Announce Type: new Abstract: In this article, we present our vision and recent advancements toward creating a decentralized system capable of learning from real-time data within buildings to support sustainable and privacy-preserving smart environments. Our approach promotes the concept of the building itself as the data center, aligning with the principles of edge computing to
arxiv Oct 3
GPU-Initiated Communication: Dissecting Down to the Bone
arXiv:2610.01380v1 Announce Type: new Abstract: GPU-initiated communication lets GPU threads post RDMA operations directly to the NIC. It underpins NVSHMEM, NCCL GIN, and DeepEP, which serve the fine-grained, latency-critical communication of Mixture-of-Experts (MoE) models, yet its performance characteristics and optimizations remain scarcely documented beyond source code, and library comparison
arxiv Oct 3
Exploiting the Interplay of Compute- and Memory-Bound kernels in MPI Applications
arXiv:2610.01587v1 Announce Type: new Abstract: Parallel applications are often designed for synchronous, lock-step execution, treating communication stalls as performance hazards. Yet, in a communication-light application without frequent synchronization points that alternates between compute-bound memory-bound execution, an MPI communication stall can act as an unintentional relief on memory-ba
arxiv Oct 3
ePACT: Energy-Performance-Aware Commitment Tracking for LLM Serving
arXiv:2610.01784v1 Announce Type: new Abstract: Reducing LLM serving energy does not by itself guarantee lower deployment cost when electricity procurement exposes operators to unfavorable deviations from preset commitments. We study hourly commitments with positive, potentially asymmetric costs for overuse and underuse, and formulate energy-Performance-Aware Commitment Tracking: minimize deviati
arxiv Oct 3
GitHub - ai-boost/awesome-harness-engineering: Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration. · GitHub
Provides a curated survey and reading list mapping design trade-offs in agent harnesses across workflows, memory, skills, and multi-agent orchestration.
web Oct 2
LBFAST: A Lightweight Moment-Represented Lattice Boltzmann Solver for Multi-GPU Architectures
arXiv:2609.09160v2 Announce Type: replace Abstract: We present LBFAST, a GPU-oriented lattice Boltzmann solver based on a lightweight moment-represented formulation, in which post-collision populations are reconstructed on the fly from a reduced set of moments rather than stored explicitly. This approach significantly lowers the memory footprint, enabling large three-dimensional simulations withi
arxiv Oct 2
When Fancy Eviction Fails: Rethinking Cache Replacement For LLM Prefix Reuse
arXiv:2609.28870v2 Announce Type: replace Abstract: Long-running LLM applications repeatedly send growing context, making prefix caching critical for reducing prefill cost. Yet prefix-cache behavior under agentic workloads remains poorly understood. We study production traces from two companies and evaluate 14 eviction algorithms across HBM-constrained and large memory-pool settings. Despite a la
arxiv Oct 2
Progressive-Resolution Secure Aggregation for Federated Learning
arXiv:2610.00695v1 Announce Type: cross Abstract: Secure aggregation lets a server recover an aggregate of client updates without observing any individual update, but conventional protocols fix the aggregate precision when clients upload. We introduce and formulate a new progressive-resolution secure-aggregation functionality in which clients upload once and successively finer resolutions of the
arxiv Oct 2
Redundancy Meets Synergy: Dependency-aware Expert Selection for MoE via Submodular Optimization
arXiv:2610.00558v1 Announce Type: cross Abstract: While Mixture-of-Experts (MoE) models effectively scale model capacity through sparse activation, their deployment is often bottlenecked by prohibitive memory requirements. Extracting a compact subset of experts presents a promising solution. However, existing expert selection heuristics predominantly rely on Top-k ranking, which isolates the eval
arxiv Oct 2
HakiCC: LLM-Driven Multi-Agent Design and Optimization of Concurrency Control Protocols
arXiv:2610.00889v1 Announce Type: cross Abstract: Large language models (LLMs) have recently been applied in systems research as a tool to reduce human-intensive engineering effort through cost-efficient automation. Decades of research have produced a rich landscape of concurrency control (CC) protocols, each encoding distinct trade-offs in correctness, throughput, and abort behavior. However, mo
arxiv Oct 2
PaxosLease Revisited: A Checked Model of Diskless Distributed Leases
arXiv:2609.14640v2 Announce Type: replace Abstract: PaxosLease is a protocol by which a quorum of acceptors grants time-bounded exclusive ownership with no durable acceptor lease state and no disk write on the lease acquisition path. This paper gives a precise, machine-checked statement of the protocol and of its standard use, electing a Multi-Paxos leader. Formalizing and model checking the orig
arxiv Oct 2
Meta-Multi-Agent Reinforcement Learning for Fast Adaptation of Interactive Policies with Applications to Autonomous Driving
Develops a meta-MARL framework using bi-level optimization to enable rapid policy adaptation across multi-agent tasks.
arxiv Oct 1
Memetic Trojans: Social Contagions as Carriers of Adversarial Payloads in Agent Networks
Defines memetic trojans as a network attack class that exploits LLM agents' retransmission tendencies, distinct from self-replicating worms.
arxiv Oct 1
Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
Introduces authorization-paired evaluation to block prohibited joint outcomes in collaborative MAS while preserving admissible contributions.
arxiv Oct 1
Understanding Issues, Causes and Solutions in Open-Source LLM-based Multi-Agent Systems
Surveys open-source LLM-based MAS practitioners to identify core challenges, root causes, and mitigation strategies.
arxiv Oct 1
Beyond Final Accuracy: Auditing Communication in LLM Multi-Agent Systems
Shows that multi-agent communication gains cannot be isolated from architecture or reasoning effects under standard evaluations, proposing disentanglement methods.
arxiv Oct 1
Flowing Faster to Coordinate: One-Step Online Multi-Agent Flow Policies
Proposes optimizations for diffusion-based generative policies in MARL to achieve expressive multimodal actions with reduced sampling cost.
arxiv Oct 1
XIM: The XDC Interledger Messaging Protocol
arXiv:2609.39310v1 Announce Type: cross Abstract: Distributed ledgers, privacy-preserving institutional networks, and conventional payment systems increasingly need to exchange authenticated messages and settle assets across heterogeneous trust domains. Existing interoperability systems typically optimize for one of three concerns: application-level abstraction, cross-chain message transport, or
arxiv Oct 1
Argus: A Real-EKS Study of When Predicting Spot Interruptions Beats Simple Checkpointing
arXiv:2609.39067v1 Announce Type: cross Abstract: Elastic Compute Cloud (EC2) Spot is 60% to 90% cheaper than On-Demand but can be reclaimed on just a 2-minute notice; for expensive multi-node training this loss can be severe, with one reclaim costing hours of synchronous progress. We build Argus, a Kubernetes operator, and ask empirically, on a CIFAR-10 testbed, when predicting interruptions bea
arxiv Oct 1
Client and Training Data Selection for Computationally Efficient Synchronized Federated Learning
arXiv:2609.39250v1 Announce Type: cross Abstract: Federated learning (FL) is a promising paradigm of machine learning, which preserves user privacy by enabling learning without sharing raw data with a cloud server. Straggling clients have been a problem for FL as they introduce delays in aggregating the local models and hence, the convergence of the global model. Therefore, it is important to hav
arxiv Oct 1
The Persona Is Still There, but Who Is Speaking? Latent Identity Reversion in Persistent AI Agents
Uses an observed dissociation incident in a persistent LLM agent to identify factors that maintain persona identity across repeated interactions and state changes.
arxiv Oct 1
CompMat-Bench: Benchmarking AI Agents for Computational Materials Science
Presents CompMat-Bench, a benchmark of 94 tasks from recent computational materials papers that evaluates agents without repeating expensive simulations.
arxiv Oct 1
EurekaBench: Measuring Agentic Ability to Discover New Scientific Insights
Explores whether AI agents can discover physical laws like Newton’s gravitation via iterative data analysis, mathematical pattern extraction, and theory refinement against observations.
arxiv Oct 1
Fault-Tolerant Budget Conservation in Distributed Multi-Agent Delegation
Formalizes fault-tolerant budget conservation mechanisms that prevent overspending in distributed multi-agent delegation despite message loss, partitions, and timeouts.
arxiv Oct 1
Worse Together: How Performance Breaks Down in Multi-User Multi-Agent Teams
Shows that multi-user, multi-agent coordination on shared resources frequently fails across five frontier models and 77 scenarios, producing worse outcomes than centralized agents.
arxiv Oct 1
Authorization for Self-Modifying AI Agent Populations: Conserving Authority across Replacement, Forking, and Rollback
Defines authorization succession, a mechanism that conserves authority across forks, rollbacks, and generations of self-modifying AI agents.
arxiv Oct 1
The Cognitive Continuity Test: Verifying Governed State Transitions in Persistent AI Agents
Proposes the Cognitive Continuity Test (CCT), a policy-relative contract that verifies authorized state transitions in persistent, self-modifying AI agents.
arxiv Oct 1
Global Coherence: When Every Agent Is Right and the Team Is Still Wrong - A Local-to-Global Semantic Foundation for Multi-Agent Collaboration
Defines the global coherence problem for AI agents and states the Observation-Aliasing Impossibility Theorem that gives the exact condition for guaranteed valid joint actions.
arxiv Oct 1
Sapien: A Stateful Policy Engine for Autonomous AI Agents
Introduces Sapien, a policy engine that enforces stateful contextual security policies on AI agent tool calls via regular expressions extended with state tracking.
arxiv Oct 1
Enabling Efficient Client Selection in FL-as-a-Service for Multi-Application based Society 5.0
arXiv:2609.38626v1 Announce Type: cross Abstract: The rapid development of the Internet of Things (IoT) has led to the generation of vast amounts of data from sensors, prompting the need for advanced learning models to analyze this data for personalized services. Federated learning (FL) emerges as a solution, offering decentralized learning that preserves user privacy by building models on local
arxiv Oct 1
Characterizing High Bandwidth Flash for LLM Serving
arXiv:2609.39131v1 Announce Type: cross Abstract: Large language model (LLM) serving requires substantial memory to store model weights and KV caches. As models grow larger and contexts become longer, memory capacity and bandwidth increasingly become bottlenecks for serving performance. Agentic workloads compound this pressure through repeated interactions over growing contexts, making it increas
arxiv Oct 1
An Island-Based Parallel Biased Random-Key Genetic Algorithm for the Three-Dimensional Trailer Loading Problem
arXiv:2609.39272v1 Announce Type: cross Abstract: The Three-Dimensional Trailer Loading Problem (3D-TLP) involves determining the optimal placement and orientation of heterogeneous items within the confined space of a trailer while maximizing volume utilization and satisfying a wide range of complex logistical and safety constraints. The 3D-TLP is NP-hard, rendering exact optimization approaches
arxiv Oct 1
Governing Agentic AI in the Administrative State: Human Oversight, Cybersecurity Accountability, and Risk in Autonomous Digital Systems
Argues that sequences of modest agent tool calls can produce consequential outcomes and shift informational power away from institutions.
web Sep 30
Federated Clustering with Unknown Local and Global Cluster Cardinalities
arXiv:2609.36762v1 Announce Type: cross Abstract: Federated clustering methods that do not require the global number of clusters $K$ still assume that each client knows its local number $K_g$. This assumption is hard to justify when clients know no more about their data than the server does, as in fault diagnosis across independently operated industrial sites. We propose a two-phase framework in
arxiv Sep 30
Recolorable Graph Exploration by an Oblivious Agent with Fewer Colors
arXiv:2505.02789v2 Announce Type: replace Abstract: Recently, B\"ockenhauer, Frei, Unger, and Wehner (SIROCCO 2023) introduced a novel variant of the graph exploration problem in which a single memoryless agent must visit all nodes of an unknown, undirected, and connected graph before returning to its starting node. Unlike the standard model for mobile agents, edges are not labeled with port numb
arxiv Sep 30
Encoding and Node Choices in Transversal Fault-Tolerant Distributed Quantum Computations: An Initial Study
arXiv:2609.37210v1 Announce Type: cross Abstract: We compare and study different Bivariate-Bicycle (BB) encodings and node choices for distributed quantum operations such as transversal non-local CNOTs. We observe that while some encodings have more physical qubits requiring more ebits for a distributed computation, reducing ebit consumption alone might not be the best criterion for selecting an
arxiv Sep 30
[Add] AI Agent Economics: Can Autonomous Economic Behavior Emerge among AI Agents under Minimal External Conditions? · Issue #54 · AO-Commons/knowledge-graph
Examines whether autonomous economic behaviors such as trade and specialization can emerge among AI agents under minimal institutional conditions.
web Sep 30
Replay the Curvature: Accurate and Scalable NVFP4 Quantization for Large Language Model Inference
arXiv:2609.36654v1 Announce Type: cross Abstract: Large language models make weight storage and memory traffic major inference costs, motivating low-precision formats that represent each weight with only a few bits. Such formats use a scale to map floating-point values into a small codebook; NVFP4 improves local range utilization by letting every 16 E2M1 weights share an E4M3 block scale. Choosin
arxiv Sep 30
CF-LoRA: Decoupled Factor Aggregation and Adaptation-Aware Client Clustering for Federated LoRA Fine-Tuning
arXiv:2609.36986v1 Announce Type: cross Abstract: Federated LoRA fine-tuning enables parameter-efficient adaptation of pre-trained models without sharing private data, but suffers from two fundamental mismatches under heterogeneous client data: a structural aggregation mismatch caused by independently averaging LoRA factors, and a statistical collaboration mismatch caused by enforcing a single gl
arxiv Sep 30
MEDEM: Multi-Engine DL Accelerator Design Methodology
arXiv:2609.37399v1 Announce Type: cross Abstract: Multi-engine deep learning (DL) accelerators are becoming increasingly prevalent as they address the heterogeneity and growing complexity of modern DL workloads. To efficiently process diverse DL workloads, these accelerators must incorporate combinations of engines with complementary capabilities to match the distinct computational characteristic
arxiv Sep 30
EfficientAgent: What Makes KV Cache Offloading Work for Concurrent Agents?
arXiv:2609.33762v1 Announce Type: new Abstract: LLM agents resend their whole conversation on every turn, and most of it was already processed on the previous turn. Serving systems avoid recomputing it by caching its key-value (KV) state and, when GPU memory runs out, by offloading that state to host memory. For agents, offloading gives inconsistent results: on the same coding-agent workload it s
arxiv Sep 29
Validating Memory-Optimal Transformer Kernels on Real Hardware: From Formal Derivation to Measured Performance Across Two HPC Clusters
arXiv:2609.33916v1 Announce Type: new Abstract: We validate memory-optimal cost functions for transformer kernels derived via the Mathematics of Arrays (MoA). Companion Papers I-IV formally derive kernels for attention forward, backward, fused forward+backward, decode, and the complete block (RMSNorm, gated MLP) as a hardware-independent specification (DNF) transformed to a machine-specific reali
arxiv Sep 29
Toward System-of-Systems Integration for Composable Cloud-HPC-Edge AI Platforms
arXiv:2609.33427v1 Announce Type: new Abstract: Modern AI platforms increasingly combine infrastructure stacks and operating models designed around different assumptions, including cloud-style service platforms, HPC workload-management systems, cloud-native orchestration, data and artifact systems, managed connectivity, observability, and edge or cyber-physical environments. Existing work demonst
arxiv Sep 29
OLED-MoE: Accelerating MoE-Based dLLM Inference via Inter-Iteration Locality-Aware Expert Offloading
arXiv:2609.33385v1 Announce Type: new Abstract: Semi-autoregressive diffusion large language models (dLLMs) improve decoding parallelism through iterative block-wise denoising, but scaling them with mixture-of-experts (MoE) layers introduces a large expert parameter footprint that exceeds memory-constrained GPU capacity. Expert offloading is a natural remedy, yet existing MoE serving systems targ
arxiv Sep 29
Adaptive Client Clustering and Coordination for Federated Learning Workflow Management in Edge Networks
arXiv:2609.33544v1 Announce Type: new Abstract: Federated learning (FL) is increasingly deployed as a managed learning service rather than as a set of isolated training jobs. In networked edge environments, dependent FL service flows must coordinate heterogeneous clients, non-IID data, fluctuating communication latency, and precedence-constrained tasks under service-level completion requirements.
arxiv Sep 29
Performance vs Portability in Heterogeneous HPC Environments: Why Pre-execution Benchmarking is Required
arXiv:2609.33847v1 Announce Type: new Abstract: Cloud computing and high-performance computing (HPC) typically follow different paradigms: cloud services are often orchestrated using Kubernetes, whereas HPC workloads are managed through batch schedulers such as Slurm. Growing demand for shared computational resources increases the need for interoperability between these environments. This study u
arxiv Sep 29
AICurate - AI-powered news curation for your industry
Describes AICurate, a digest service that compiles and summarizes selected articles on a user-chosen daily or weekly schedule.
web Sep 28
Unifying AI-assisted scientific discovery around exploration, hypothesis generation, and testing - ScienceDirect
Surveys LLM-agent frameworks (Chain of Ideas, SciAgents, AI-Scientist) that generate queries, retrieve literature via APIs, and curate datasets for research novelty checks.
web Sep 28
Autonomous Event-Driven Multi-Agent Orchestration for Enterprise AI at Scale
Presents a continuous-event simulation benchmark for evaluating enterprise multi-agent coordination beyond discrete request-response workflows.
web Sep 28
2026-09-28 Agentic Economies for Autonomous Scientific Discovery
Explores agentic economies enabling autonomous scientific discovery through coordinated AI agent interactions.
web Sep 28
GitHub - aloth/awesome-ai-agents: A curated list of AI agent frameworks, tools, platforms, research papers, and resources · GitHub
Curates a collection of 2026 AI-agent papers covering engineering, memory, evaluation, workflows, and autonomous systems.
web Sep 28
AI Tools for Research - Artificial Intelligence (Generative) Resources - Guides at Georgetown University
Lists guides and resources for generative AI tools applicable to academic research.
web Sep 28
[2609.36362] Strategies for Deploying AI Agents in Production at Scientific User Facilities
Outlines strategies for deploying AI agents in production at scientific user facilities.
web Sep 28
Deduplication-while-Training: A Resilient Paradigm for Privacy-Preserving Cross-Client Deduplication in Federated Learning
arXiv:2609.31262v1 Announce Type: cross Abstract: Cross-client duplicate data in large language model training corpora degrades the efficiency of federated learning (FL) while exacerbating model memorization and privacy risks. Privacy-preserving cross-client deduplication effectively mitigates this issue by eliminating duplicate training data. However, existing schemes all follow a "Deduplication
arxiv Sep 28
Momentum-Guided Federated Split Distillation for Personalized Temporal Edge Intelligence
arXiv:2609.31159v1 Announce Type: cross Abstract: We propose a momentum-guided federated split distillation framework for personalized, efficient, and autonomous temporal edge intelligence. We introduce TeRR-SAtt, our novel temporal reservoir student attention design that combines fixed reservoir representations, a lightweight temporal student, and personalized output modules. We also present AMG
arxiv Sep 28
Beyond the Last Truffula Tree: SustainAI - A Water-Aware, Closed-Loop Framework for Environmentally Accountable AI
arXiv:2609.30747v1 Announce Type: cross Abstract: As artificial intelligence (AI) becomes embedded in everyday life, its environmental footprint, particularly water consumption remains largely invisible. While energy and carbon impacts are widely recognized, the substantial freshwater demands of data center cooling and electricity generation receive little attention. To address this gap, we intro
arxiv Sep 28
🌐 Official AI Content Report 2026-09-29 · Issue #1498 · stevenko2002/agents-radar
Reports Anthropic's release of a multi-agent economic interaction paper (Project Swap) alongside an Infosys partnership for enterprise agent deployment.
web Sep 28
FRESHLATENT: Channel-Aware Latent Adaptation for Resource-Constrained Embodied VLM Perception
arXiv:2609.30629v1 Announce Type: cross Abstract: Mission-critical UAVs increasingly rely on split vision-language model (VLM) perception under tight onboard-resource and wireless-communication constraints. However, corruption of transmitted intermediate features creates a deployment mismatch for clean-trained split interfaces, while stronger channel-aware codecs can impose substantial onboard co
arxiv Sep 28
Distributed Learning as a Service: The Developer's Perspective
arXiv:2609.31061v1 Announce Type: cross Abstract: Application developers of distributed learning services face challenges that a typical federated learning loop does not address. Specifically, the model updates can still leak private data, devices might not be able to participate in the training due to limited resources, a single aggregator might not be able to scale, and the transmissions of mod
arxiv Sep 28
Deterministic Regime Switching and Feasibility Inversion in Dynamic Tensor Rematerialization
arXiv:2609.31250v1 Announce Type: cross Abstract: We report fine-grained, deterministic instability in Dynamic Tensor Rematerialization (DTR), an online eviction policy for memory-constrained DNN training, measured on the reference DTR simulator (simrd) using public execution traces. On an LSTM trace, memory budgets differing by 0.10% of unconstrained peak memory select fast and slow execution re
arxiv Sep 28
Citation and Attribution - Generative Artificial Intelligence - LibGuides at Brown University
Specifies citation format treating the AI tool as author, including generation date and optional prompt description in footnotes.
web Sep 27
Where Does the Energy Go? Profiling LLM Agent Inference on Blackwell GPUs
arXiv:2609.29707v1 Announce Type: new Abstract: LLM agents that iteratively reason, plan, and invoke tools create workload profiles fundamentally different from single-pass inference, yet how their energy consumption is distributed across hardware components and workload phases remains poorly understood. Characterizing these workloads therefore requires simultaneous visibility into both component
arxiv Sep 27
Concurrent Split Learning Through Stable Client Clustering
arXiv:2609.29395v1 Announce Type: new Abstract: Training with a fixed global batch limits how many distributed clients can provide examples in any one step. We examine a way to use additional server workers without increasing the batch processed by an individual workload. Global Clustered Parallel Split Learning (GCPSL) assigns clients to fixed clusters, executes a Parallel Split Learning with Gl
arxiv Sep 27
Cross-Model Autoscaling for Shared LLM Serving
arXiv:2609.29160v1 Announce Type: new Abstract: Multi-model LLM serving is moving toward shared MaaS clusters, where co-hosted models compete for a fixed GPU budget while each model experiences time-varying demand and must satisfy its own latency SLO. Existing LLM autoscalers remain largely model-local: their signals expose local runtime activity or delayed latency outcomes, and their scale-up or
arxiv Sep 27
Dependency- and Layer-Aware Microservice Workflow Offloading and Service Image Caching for Edge Environments
arXiv:2609.28943v1 Announce Type: new Abstract: The microservice architecture has been applied broadly in many mainstream computing environments. As one of the most prevalent environments, edge computing also widely employs microservices to handle diverse requests and tasks. In practical scenarios, microservices usually constitute workflows that are built based on service dependencies to execute
arxiv Sep 27
TrafficFab: An Autonomic Edge-Cloud Testbed Fabric forAI-Driven Traffic Management
arXiv:2609.29223v1 Announce Type: new Abstract: Traffic management in emerging megacities requires real-time analytics over thousands of CCTV video streams under latency, bandwidth, compute and energy constraints. We present TrafficFab, an autonomic edge--cloud testbed for AI-driven traffic management, designed to validate a representative slice of a megacity deployment. TrafficFab combines RTSP
arxiv Sep 27
Resource-Aware Model Selection for Scalable Indoor Localization on HPC Platforms
arXiv:2609.29402v1 Announce Type: new Abstract: Large-scale indoor localization is increasingly needed in campuses, smart buildings, factories, and digital-twin infrastructures, where wireless conditions, access-point deployments, and spatial layouts evolve over time. Such systems must be accurate, extendable, and maintainable, allowing new buildings, floors, rooms, and service areas to be added
arxiv Sep 27
A Block Decomposed QUBO Workflow for Chromosome-Y Phylogeny Reconstruction
arXiv:2609.29856v1 Announce Type: new Abstract: This paper sets out a computational workflow that reconstructs the phylogeny of human Y-chromosome populations from a Variant Call Format (VCF) file of biallelic Single Nucleotide Polymorphisms (SNP). The two classical phylogenetic decisions - topology selection and root placement - are cast as Quadratic Unconstrained Binary Optimisation (QUBO) prob
arxiv Sep 26
Adaptive Tiling for Least-Squares Phase Unwrapping: Runtime and Accuracy
arXiv:2609.28541v1 Announce Type: cross Abstract: Phase unwrapping estimates the missing multiples of $2\pi$ in measured phase images. For large images, tiling limits the size of local reconstruction problems and enables parallel processing. Adaptive tiling could further reduce the number of local problems and boundaries by retaining large tiles where little refinement is needed. We investigate w
arxiv Sep 26
KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization
arXiv:2609.30059v1 Announce Type: new Abstract: Deep learning inference and training performance depends critically on GPU kernel efficiency. Modern compilers such as PyTorch Inductor automatically generate GPU kernels from high-level model code, but frequently underperform expert-written implementations by wide margins. Recent LLM-assisted kernel optimizers can close this gap for standalone kern
arxiv Sep 26
Reusing Spare Vehicle Computing Capacity: Is It Viable, Profitable and Sustainable?
arXiv:2609.29731v1 Announce Type: new Abstract: Vehicular Cloud Computing (VCC) exploits computing hardware already embedded in vehicles for purposes unrelated to offloading and puts its idle cycles to work executing end-users' offloaded tasks, avoiding the deployment of new computation infrastructure. Despite its conceptual appeal, adoption is hindered by the lack of quantitative evidence that s
arxiv Sep 26
KREX: Concurrent Kernel Benchmarking on Shared GPUs via Region-Granular Exclusivity
arXiv:2609.30057v1 Announce Type: new Abstract: LLM agents automate GPU kernel optimization by repeatedly composing candidates and measuring their duration on real GPUs. Existing systems preserve measurement fidelity by reserving a GPU for an entire agent session or benchmarking command. However, this results in poor utilization because only a small fraction of command execution requires exclusiv
arxiv Sep 26
Steelhead: Interleaving Partially Synchronous and Asynchronous Commit Rules on a Shared DAG
arXiv:2609.30163v1 Announce Type: new Abstract: Dual-mode consensus protocols are fast when the network is partially synchronous and remain live under asynchrony. We introduce Steelhead, a dual-mode mechanism that composes a partially synchronous and an asynchronous commit rule over one DAG: every k-th round is decided by the asynchronous rule, whose leader a common coin reveals after the votes,
arxiv Sep 26
Artificial Intelligence | Cool Papers - Immersive Paper Discovery
Reports practical design choices for deploying Neuro-Symbolic methods in an industrial configuration copilot and identifies scaling challenges for trustworthy engineering AI.
web Sep 25
Paper2agent Turns Static Papers Into Live AI Tools - IEEE Spectrum
Presents Paper2Agent, an open-source framework that converts papers plus codebases into tested, interactive AI agents runnable on new datasets.
web Sep 25
[2609.31562] Agentic Economies for Autonomous Scientific Discovery
Outlines infrastructure foundations for scientific agent economies, markets, and institutions to manage AI resources.
web Sep 25
[2609.31219] Research with AI Agents: How Agentic Systems Are Changing Scientific Work
Examines how agentic AI systems are transforming scientific workflows across task design, execution, evaluation, and knowledge curation.
web Sep 25
Sluice: Global Invariant, Local Enforcement for Pooled Payment-Channel Liquidity
arXiv:2609.29975v1 Announce Type: cross Abstract: A routing node on the Lightning Network holds its liquidity in separate channels, so a payment can fail at a channel whose outbound balance is exhausted while the node's other channels still hold balance. Pooling the channels into one reserve fixes this only if the node's draws across all channels stay within the reserve: a global invariant that e
arxiv Sep 25
The HEAL Data Platform
arXiv:2512.17506v2 Announce Type: replace Abstract: Objective: The objective was to develop a cloud-based, federated system to serve as a single point of search, discovery and analysis for data generated under the NIH Helping to End Addiction Long-term (HEAL) Initiative. Materials and methods: The HEAL Data Platform is built on the open source Gen3 platform, utilizing a small set of framework s
arxiv Sep 25
MagiCFirm: A Runtime for Magic-State Cultivation with Algorithm-Hardware Co-Design
arXiv:2609.29267v1 Announce Type: cross Abstract: Magic-state cultivation offers a promising alternative for lowering the cost of non-Clifford operations in fault-tolerant quantum computing (FTQC). However, realizing cultivation in practice exposes two challenges: (i) the lack of an open-source classical runtime layer between logical software and physical control, and (ii) the latency constraints
arxiv Sep 25
Security Limits of Mining Before Validation in Nakamoto Consensus
arXiv:2609.29222v1 Announce Type: cross Abstract: Mining before validation allows miners to extend a newly received block before completing its validity checks, giving them a head start in the race for the next block reward. This head start, however, comes with a security risk: rejecting one invalid block also discards the honest work built on it, an effect missed when validation is treated as in
arxiv Sep 25
Rolling Round-Robin Rate: Standard Heterogeneous Throughput for SPEC CPU
arXiv:2609.29681v1 Announce Type: cross Abstract: SPEC CPU has long provided a common foundation for comparing processor, compiler, memory-system, and platform performance. Its multi-copy SPECrate mode measures homogeneous throughput by running many copies of the same benchmark at once. That mode remains valuable, but modern cloud and server systems commonly run heterogeneous collections of jobs
arxiv Sep 25
Agora: A System for Consumption-Based GPU Pricing
arXiv:2510.05111v2 Announce Type: replace Abstract: We present Agora, a lightweight system designed for cloud-based GPUs which meters a three-dimensional resource vector from commodity performance counters and prices it with a function that charges customers based on resources used rather than time spent renting. Because the calibration is revenue-neutral, any gain must come from demand the flat
arxiv Sep 25
AMP: Arc Multi-Proposer Protocol with Bounded Inclusion Guarantees
arXiv:2605.23677v2 Announce Type: replace Abstract: Blockchain systems that settle financial transactions face a structural tension: the validator that assembles each block holds unilateral power over transaction inclusion and ordering. Traditional markets curb this power through laws that prevent front-running and market manipulation. Regulators have flagged the absence of such rules as a first-
arxiv Sep 24
Scheduling Coflows in Multi-Core OCS Networks with Performance Guarantee
arXiv:2604.08242v5 Announce Type: replace Abstract: The coflow abstraction captures application-level communication patterns and enables coordinated scheduling of parallel flows to reduce job completion times in distributed systems. Modern data center networks (DCNs) are employing multiple independent optical circuit switching (OCS) cores operating concurrently to meet the massive bandwidth deman
arxiv Sep 24
Source-Known Identifiers: A Three-Tier Identity System for Distributed Applications
arXiv:2604.00151v2 Announce Type: replace Abstract: Distributed applications use identifiers across database storage, trusted communication, and external access. Depending on their use, these roles require different combinations of storage efficiency, chronological sortability, origin metadata embedding, zero-lookup verifiability, metadata confidentiality, and multi-century addressability. The id
arxiv Sep 24
Learning to Remember: Attentive Reinforcement Learning for Edge Serverless Autoscaling
arXiv:2603.28790v2 Announce Type: replace Abstract: In edge computing, the stochastic and bursty nature of serverless workloads challenges autonomous resource orchestration. Traditional reactive controllers, such as the Kubernetes Horizontal Pod Autoscaler (HPA), suffer from reaction latency, leading to Service Level Objective (SLO) violations during traffic spikes and resource flapping during ra
arxiv Sep 24
EXaCTz: Guaranteed Extremum Graph and Contour Tree Preservation for Distributed- and GPU-Parallel Lossy Compression
arXiv:2604.01397v2 Announce Type: replace Abstract: This paper introduces EXaCTz, a parallel algorithm that corrects lossy-compressed scalar field data to preserve extremum graphs and contour trees concurrently. While error-bounded lossy compression is essential for large-scale scientific simulations and workflows, existing topology-preserving methods suffer from (1) a significant throughput disp
arxiv Sep 24
PipeLive: Efficient Live In-place Pipeline Parallelism Reconfiguration for Dynamic LLM Serving
arXiv:2604.12171v2 Announce Type: replace Abstract: Pipeline parallelism (PP) is widely used to partition layers of large language models (LLMs) across GPUs, enabling scalable inference for large models. However, existing systems rely on static PP configurations that fail to adapt to dynamic settings, such as serverless platforms and heterogeneous GPU environments. Reconfiguring PP by stopping an
arxiv Sep 24
What are AI Agents?- Agents in Artificial Intelligence Explained - AWS
Defines AI agents, their enterprise value, and integration approaches with AWS services.
web Sep 24
Persistent Billable State: Denial-of-Wallet Attacks and Defenses in Tool-Calling LLM Agents
Identifies a metering vulnerability in tool-calling LLM agent runtimes where external tool returns can be charged multiple times across conversation turns.
web Sep 23
LabFactory:Building and Evaluating Executable AI Labs
Examines whether LLM agents can package scientific workflows into persistently invocable systems after task completion.
web Sep 23
Quantum Advantage for Distributed Symmetry Breaking
arXiv:2609.26788v1 Announce Type: cross Abstract: We present a distributed quantum algorithm that $3$-colors cycles in $O(1)$ rounds, with high probability. It follows that all locally checkable labeling problems (LCLs) that have round complexity $O(\log^* n)$ in the classical LOCAL model can be solved in $O(1)$ rounds in the quantum-LOCAL model, with high probability; this includes problems such
arxiv Sep 23
PRISM: Probabilistic Runtime Insights and Scalable Performance Modeling for Large-Scale Distributed Training
arXiv:2510.15596v3 Announce Type: replace Abstract: Large model training beyond tens of thousands of GPUs is an uncharted territory. At such scales, disruptions to the training process are not a matter of if, but a matter of when -- a stochastic process degrading training productivity. Dynamic runtime variation will become increasingly more frequent as training scales and GPUs are operated in inc
arxiv Sep 23
The Fleet Is the Model: Engineering Collective Intelligence with Fusion-MoA Pioneer R1
arXiv:2609.26080v1 Announce Type: cross Abstract: The model exposed to an application need not be a single checkpoint; it can be a governed fleet. Existing serving systems manage checkpoints and replicas, while multi-agent frameworks compose model calls without defining a stable collective identity, effect authority, or member-level evolution. We present Fusion-MoA, a runtime that exposes indepen
arxiv Sep 23
Flux: Optimal Scheduling of Optical Circuit Switches for LLM Training
arXiv:2609.25949v1 Announce Type: cross Abstract: Optical Circuit Switching (OCS) offers high bandwidth density and energy efficiency for LLM training, but incurs a non-negligible reconfiguration delay. Prior work typically schedules optical circuit switches independently of compute, using aggregate traffic demand to determine which circuits to provision and when. We argue that this separation cr
arxiv Sep 23
SARA: SLO-Aware Resource Allocation for Disaggregated Agentic LLM Services
arXiv:2609.26763v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) are driving the emergence of multi-modal and agentic services for mobile users through cloud and edge infrastructures, where long-context workloads pose daunting challenges for inference latency. Existing disaggregated LLM serving systems largely rely on hardware profiling, configuration enumeration,
arxiv Sep 23
Fast and Robust Information Spreading in the Noisy PULL Model
arXiv:2411.02560v3 Announce Type: replace Abstract: Efficient information spreading in stochastic multi agent systems is a core challenge when communication is noisy, bandwidth limited, and agents lack global coordination. Yet biological systems, including ant colonies and fish schools, routinely overcome these constraints. A small number of informed individuals can reliably guide large, uncoordi
arxiv Sep 23
[2506.02153] Small Language Models are the Future of Agentic AI
Argues that small language models are more suitable and economical than large foundation models for the repetitive, specialized invocations typical of agentic systems.
web Sep 22
A Threat Modeling Prioritization and Automation Framework for Composable Architectures | MDPI
Describes enterprise shift toward composable architectures incorporating autonomous agents and microservices.
web Sep 22
Analytical Power-Aware Provisioning for Prefill-Decode Disaggregated AI Inference
arXiv:2609.24639v1 Announce Type: new Abstract: Power availability increasingly constrains the operation of AI inference fleets, creating a need for provisioning methods that jointly consider serving capacity and power consumption. Prefill--decode (PD) disaggregation has emerged as a prevalent architecture for large-scale inference serving. However, determining the appropriate numbers of prefill
arxiv Sep 22
Tiga: Compiling Graph Message Passing at Scale
arXiv:2609.24802v1 Announce Type: new Abstract: Graph message passing offers a common way to express learning algorithms, physical simulations, and numerical solvers. Efficient execution depends on interaction structure and data movement, which can be obscured when a program is expressed as a sequence of tensor operations. On memory-constrained systems such as laptops, materializing connectivity
arxiv Sep 22
Conduit: An Experience Data Plane for Distributed Reinforcement Learning
arXiv:2609.24456v1 Announce Type: new Abstract: Distributed reinforcement learning (RL) scales training by parallelizing actors and learners around an Experience Buffer. As RL workloads grow, however, the buffer becomes more than a replay queue: it is the storage substrate of a large-capacity, latency-critical experience path that every iteration traverses to move, transform, sample, and batch ex
arxiv Sep 22
Research autonomous agents and agent planning · Issue #334 · MundakaZgz/ai-homeops
Presents autonomous agent platform for remote property maintenance using persistent memory and human-in-loop orchestration.
web Sep 22
Toward GPU-Resident Climate Models: A Feasibility Study on Lossy Compression for the Spherical Harmonic Transform's Communication Bottleneck
arXiv:2609.24294v1 Announce Type: new Abstract: Operational pseudospectral atmospheric models such as the ECMWF Integrated Forecasting System (IFS) run today almost exclusively on CPUs; GPU ports are under active development but not yet used in production. These models rely on the Spherical Harmonic Transform (SHT). Each time-step requires forward and inverse SHTs, and both passes depend on globa
arxiv Sep 22
Bridging the Vendor Gap: Enabling AMD GPU Support for Awkward Array via ROCm/HIP for the HL-LHC Era
arXiv:2609.24628v1 Announce Type: new Abstract: The High-Luminosity LHC (HL-LHC) will demand order-of-magnitude gains in analysis throughput, and increasingly those gains must come from GPUs that are not made by a single vendor. Leadership-class systems such as El Capitan, Frontier and LUMI are built on AMD accelerators, yet the Scikit-HEP analysis stack---and Awkward Array in particular---has gr
arxiv Sep 22
Mitigating Front-Running Attacks through Fair and Resilient Transaction Dissemination
arXiv:2609.24713v1 Announce Type: new Abstract: In modern blockchains, efficient, fair, and faulttolerant information dissemination is critical for performance and security. Several stages of the transaction lifecycle are affected, from the creation and dissemination of transactions to the dissemination of blocks in the consensus layer. Mempool protocols, such as L{{\O}}, already address some of
arxiv Sep 22
[2609.24664] Agentic AI Enabling Autonomous, Self-Organizing, and Evolving UAV Networks
Proposes agentic AI for enabling autonomous, self-organizing, and evolving UAV networks.
web Sep 21
FedeRage: Provably Convergent Agnostic Federated Learning under General Client Drift
arXiv:2609.21057v1 Announce Type: cross Abstract: Federated learning (FL) enables collaborative model training without sharing raw data, but its performance degrades under non-IID data and stochastic client participation. Remedies built on classical Federated Averaging (FedAvg) typically presuppose that client participation probabilities are known to the server, which is rarely the case in deploy
arxiv Sep 21
Hybrid GPU-CPU Retrieval for Personalized Search at Ultra-Large Scale
arXiv:2609.21281v1 Announce Type: cross Abstract: Embedding-based retrieval on user-generated content at the trillion-document scale exposes a sharp conflict between two production demands: deep, expressive personalization for queries with rich user intent, and broad coverage of a massive inventory under fixed latency and resource budgets. We characterize this as the personalization-scale paradox
arxiv Sep 21
Verifiable Computation with Trusted Execution Environments and On-Chain Digital Rights Tokens
arXiv:2609.21728v1 Announce Type: cross Abstract: We present an architecture that enables data owners to combine private data into data pools using Trusted Execution Environments (TEEs) and manage these pools by issuing narrowly scoped computational rights, encoded as Digital Rights Tokens (DRTs), to third-party data analysts. Each DRT binds specific open-source code to a pool and is issued and r
arxiv Sep 21
Decomposing Predictive Kubernetes Autoscaling for Large Language Model Serving Under Long Startup Delays
arXiv:2609.20874v1 Announce Type: cross Abstract: Large language model (LLM) inference deployed on Kubernetes faces an autoscaling challenge that conventional web services do not: new serving replicas take two to ten minutes to start because multi-gigabyte model weights must be loaded, which makes purely reactive scaling structurally late. We ask a sharp question: among the components of a predic
arxiv Sep 21
Adapting the Actor Model of Concurrency for High-Frequency Trading: Synchronous Message Delivery (fast_send) and a Tick-to-Book Latency Study
arXiv:2609.21173v1 Announce Type: cross Abstract: The actor model - state isolation, data-race freedom, deadlock resistance, and sequential single-message reasoning - has long been dismissed as unsuitable for high-frequency trading (HFT): actors seem to imply many threads, a mailbox per actor, and a heap-allocated message plus a context switch per interaction, overhead incompatible with a microse
arxiv Sep 21
TrustBOM: A Scalable Architecture for Confidentiality-Preserving SBOMs Across Organizations
arXiv:2609.21419v1 Announce Type: cross Abstract: Software Bills of Materials (SBOMs) have emerged as a key mechanism for software supply chain governance in enterprise architectures. However, their adoption across organizations remains limited due to concerns about exposing sensitive dependency information. To address this limitation, we propose TrustBOM, a scalable architecture for confidential
arxiv Sep 21
Accelerating Sharded Data Parallelism at Scale with Federated Learning
arXiv:2609.20359v1 Announce Type: new Abstract: The symbiotic scaling of artificial intelligence models and high-performance computing systems continually creates algorithmic challenges in their convergence. Foundation models (FMs) are a crucial example, requiring months-long training on thousands of cutting-edge GPUs. Sharded data parallelism (DP) is the dominant strategy to accelerate such comp
arxiv Sep 20
VERA: Reinforcement Learning for Dynamic Memory Scaling of HPC Workloads in Kubernetes
arXiv:2609.19936v1 Announce Type: new Abstract: Memory over-provisioning results in resource underutilization when HPC workloads run on Kubernetes. The default Vertical Pod Autoscaler (VPA) cannot anticipate phase-driven memory spikes for first-run HPC jobs. In this work, we present a reinforcement learning (RL) recommender VERA that formulates vertical memory scaling as a Markov Decision Process
arxiv Sep 20
Distributed Edge Inference: an Experimental Study on Multiview Detection
arXiv:2609.20009v1 Announce Type: new Abstract: Computing is evolving rapidly to cater to the increasing demand for sophisticated services, and Cloud computing lays a solid foundation for flexible on-demand provisioning. However, as the size of applications grows, the centralised client-server approach used by Cloud computing increasingly limits the applications' scalability. To achieve ultra-sca
arxiv Sep 20
The Life of a Token: from Words to Bits on the Wire
arXiv:2609.19924v1 Announce Type: new Abstract: Large Language Models (LLMs) transform vast collections of unstructured text into semantic patterns used for language generation and reasoning tasks. Behind their ease of use lies a complex process: words become tokens, tokens become vectors, and vectors ultimately give rise to streams of bits that flow through High-Performance Computing (HPC) syste
arxiv Sep 20
P-GADMM: Parallel Group-Based ADMM for Asynchronous Optimization in Heterogeneous Edge Networks
arXiv:2609.20006v1 Announce Type: new Abstract: The Alternating Direction Method of Multipliers (ADMM) is widely used for distributed optimization, but its synchronous implementation can suffer from efficiency loss in heterogeneous edge networks, where fast clients or groups need to wait for slower ones before global updates can be completed. Existing group-based ADMM methods reduce communication
arxiv Sep 20
The Price of Decentralization, Paid Twice: A Latency Floor and a Minimal Subsidy from a Geographic Decentralization Invariant
arXiv:2609.20322v1 Announce Type: new Abstract: Latency-aware validator selection---rewarding validators for low network latency through voting weight, leadership, or fast-quorum membership---is known to push validators to co-locate, eroding the geographic fault-independence that Byzantine fault tolerance assumes. We give this tension a sharp, protocol-agnostic form. Calling a stake configuration
arxiv Sep 20
Agentic Artificial Intelligence in Agriculture: A Systematic Mapping Review of Reported Architectures, Applications, Challenges, and Future Directions
Applies multi-agent systems to agriculture challenges including climate variability and resource efficiency.
web Sep 19
General Collaborative Intelligence: Architecting Cognition for Resilient Multi-Agent Ecosystems
Describes the shift of multi-agent unmanned systems from ego-centric sensing to collaborative intelligence through compact feature exchange that overcomes local observation limits.
web Sep 19
Efficiently Distributed Federated Learning
arXiv:2609.19972v1 Announce Type: cross Abstract: Federated Learning (FL) is experiencing a substantial research interest, with many frameworks being developed to allow practitioners to build federations easily and quickly. Most of these efforts do not consider two main aspects that are key to Machine Learning (ML) software: customizability and performance. This research addresses these issues by
arxiv Sep 19
PixelFlow: Token-Level Workload Management for Efficient Distributed DiT Serving
arXiv:2609.20723v1 Announce Type: new Abstract: Online image generation with Diffusion Transformers (DiTs) must meet latency service-level objectives (SLOs) while using GPU resources efficiently. Existing systems improve GPU utilization by batching multiple requests for joint execution. However, request-level batching offers limited control over batch size: batches may be too small to saturate GP
arxiv Sep 19
Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling
arXiv:2609.19499v1 Announce Type: cross Abstract: Test-time scaling can improve large language model reasoning by generating and combining multiple candidate responses. In sampling-based methods, the inference budget is often described by the number of generated candidates, N. However, N tells us how many candidates are generated, not how they are executed. The same candidate budget can be produc
arxiv Sep 19
A Kubernetes-Native Request Router for Quality-Aware Inference Serving in the Computing Continuum
arXiv:2609.20497v1 Announce Type: new Abstract: We introduce Adaptive Score-based Routing Balancer (ASRB), a dynamic, score-based request routing mechanism for Kubernetes-based service deployments over the computing continuum. ASRB jointly considers infrastructure-level information, response time measurements, and application-level quality indicators, with a particular focus on serving Machine Le
arxiv Sep 19
SiliconBench: Speed, Memory, and Fidelity for LLM Serving on Unified-Memory Desktops
arXiv:2609.19169v1 Announce Type: cross Abstract: Concurrent local LLM serving on unified-memory desktops must preserve memory headroom and output fidelity, which speed-only rankings overlook. We introduce SiliconBench, which evaluates nine Apple Silicon serving engines through three lenses: speed, memory, and fidelity. We evaluate chat and agent serving on Qwen3, Qwen3.5, and Gemma 4. We use a c
arxiv Sep 19
Reputation as Community Memory for the Agentic Web
arXiv:2609.19502v1 Announce Type: cross Abstract: Agents can now externalize experience into memory, consolidating historical traces into semantic knowledge and procedural shortcuts that persist between sessions. Such memory is typically private to a single agent. We argue that agentic memory benefits from being collective, because trustworthy knowledge of the shared environment---the data source
arxiv Sep 19
SUIA Price Prediction , SUIA Price Prediction , Price Prediction 2025 | Bitget
Provides a forecasting tool and sentiment explorer for SUIA token prices from 2025–2050.
web Sep 19
A Study on Locally Runnable Large Language Models for Bearing Fault Diagnosis
Evaluates diagnostic accuracy achievable by LLM agents for bearing fault diagnosis when restricted to free, offline commodity hardware.
web Sep 19
From Pipelines to Autonomous Agents: The Evolution of Software Ecosystems and the Emergence of Machine Intent – eTecnogigz Writers
Traces the shift from pipeline-based software to autonomous agents that embed machine intent in desktop ecosystems.
web Sep 19
AI or Real: Detecting Partially Altered Videos Under Resource-Constrained Environments
arXiv:2609.20263v1 Announce Type: cross Abstract: The proliferation of generative video models has shifted the practical detection threat from fully fabricated clips to partially manipulated footages. Although modern detectors achieve strong accuracy using foundation backbones of 400M+ parameters, their resource footprint precludes edge deployment. In this paper, we present a lightweight full-fra
arxiv Sep 18
Efficient Non-Uniform Quantum Hermite Transform through Adaptive Sampling
arXiv:2609.20739v1 Announce Type: cross Abstract: On the span of the first $N$ oscillator modes, Gauss--Hermite quadrature gives an exact change of basis between mode coefficients and $N$ weighted position space samples. We implement this transform with $O(N\operatorname{polylog}(N,1/\varepsilon))$ logical gates and polylogarithmic quantum width. The operator-error bound $\varepsilon$ holds on ar
arxiv Sep 18
FedeRICo: Federated Region-Influenced Coupling for Traffic Flow Prediction
arXiv:2609.20026v1 Announce Type: cross Abstract: Urban traffic forecasting often relies on information distributed across stakeholders who may be unable to share raw data due to privacy or commercial constraints, motivating federated spatial-temporal approaches. In such federated settings, each client observes traffic over a distinct sensor subgraph with its own spatial topology and temporal dyn
arxiv Sep 18
XIR: A Framework for Interoperability across Cross-Chain Protocols Based on a Verifiable Intermediate Representation
arXiv:2609.20010v1 Announce Type: cross Abstract: Cross-chain protocols enable applications to exchange messages across blockchains. Under point-to-point configurations, communication depends on a direct connection between the source and destination blockchains, limiting blockchain reachability and requiring additional configurations to connect more blockchains. To quantify this problem, this pap
arxiv Sep 18
Competition, Collusion, and Corruption: The Spectrum of MEV Attacks on DAG-Based BFT Consensus Protocols
arXiv:2609.20069v1 Announce Type: cross Abstract: Byzantine Fault-Tolerant (BFT) protocols guarantee safety and liveness despite the malicious failure of nodes. However, they do not prevent adversarial manipulation of transaction order, where the order a proposer assigns diverges from the order in which clients submitted their transactions. Exploiting this discretion for profit is known as maxima
arxiv Sep 18
Multi-center Medical Data Mining with FL-Net - A One-stop Shop for Federated Learning
arXiv:2609.20650v1 Announce Type: cross Abstract: Federated learning enables collaborative training without sharing patient-level data, but most studies remain simulations. Based on five requirements derived from the literature, we analyzed 14 FL frameworks and found that none fully satisfied these requirements. We present FL-Net, a novel federated clinical research framework to fulfill all requi
arxiv Sep 18
Multi-agent system - Wikipedia
Defines a multi-agent system as multiple interacting intelligent agents that collectively solve problems intractable for single agents or monolithic systems.
web Sep 18
AI tool turns any paper into an ‘agent’ that can collaborate and answer complex queries | Nature
Presents Paper2Agent, a tool that converts static research papers into dynamic AI agents capable of answering questions and applying methods to new data.
web Sep 17
Intelligent agent - Wikipedia
Defines an intelligent agent as an entity that perceives its environment and acts autonomously to achieve goals, potentially via learning.
web Sep 17
Autonomous agent - Wikipedia
Defines an autonomous agent as an AI system capable of independent, purposeful action in the real world.
web Sep 17
Fathom: Per-Query Read Depth for Sparse Decoding over Offloaded KV Caches
arXiv:2609.17652v1 Announce Type: cross Abstract: When agentic sessions run to a million tokens with many sessions resident at once, the KV cache and the index that ranks it live in host memory, and the scan that ranks all n keys for a top-k step becomes the traffic that bounds decoding. We present Fathom, a key scan in which each query decides how many bits of each key channel to read. The 4-bit
arxiv Sep 17
vidax: A Unified JAX Framework for Video Generative Models on Accelerator Meshes
arXiv:2609.18077v1 Announce Type: cross Abstract: Open-source video generative models ship almost exclusively as PyTorch/CUDA reference implementations. This leaves Cloud TPU pods without a production-ready inference path, despite offering large, cost-effective accelerator memory pools ideal for long-sequence spatiotemporal attention. We present vidax, an open-source JAX/Flax inference engine and
arxiv Sep 17
GroupKV: Hierarchical KV Cache Management for Long-Context Diffusion LLM Inference
arXiv:2609.17573v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) are emerging as a promising generative paradigm that complements autoregressive decoding. In long-context settings, KV cache bloat and offloading transfer overhead have become primary bottlenecks in inference systems. Meanwhile, the periodic full-sequence recomputation and localized token updates in dLLMs ma
arxiv Sep 17
An energy-aware federated intelligence framework for sustainable WSN-IoT ecosystems | Peer-to-Peer Networking and Applications | Springer Nature Link
Shows CNNs, RNNs, and reinforcement learning enable WSN-IoT systems to deliver real-time analytics, fault detection, and adaptive security beyond raw data collection.
web Sep 17
Cooperative multi-agent reinforcement learning with entangled state representations and copula-based action coordination for urban navigation | Computational Statistics | Springer Nature Link
Demonstrates cooperative multi-agent control policies learned via deep reinforcement learning in multi-agent settings.
web Sep 17
BLADE: ReliaBle Dynamic Hardware-Aware SNN-ANN Boundary SeLection for Event-BAseD Object DEtection
arXiv:2609.17562v1 Announce Type: cross Abstract: Hybrid Spiking Neural Network (SNN)-Artificial Neural Network (ANN) architectures combine the energy efficiency of SNNs with the superior detection accuracy of ANNs for event-based object detection. Existing hybrid SNN--ANN networks, however, employ static inference and select the SNN-ANN boundary primarily according to accuracy and energy consump
arxiv Sep 17
State Without a Landlord: An Architecture Proposal for Peer-to-Peer Replication of Durable Workflow State
arXiv:2609.17645v1 Announce Type: cross Abstract: Durable-execution frameworks commonly journal execution steps of a long-running function and reconstruct state by deterministic replay; the journal is therefore the workflow's authoritative state, and in current deployments it typically resides with whichever provider hosts the run. This paper examines what changes if the journal is instead an aut
arxiv Sep 17
ASPIRE: Asynchronous Batched Self-Speculative Decoding for Long-Context LLM Inference
arXiv:2609.17943v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by attention, whose repeated KV-cache reads make decoding memory-bound. Self-speculative decoding alleviates this by drafting tokens with sparse attention and verifying them with full attention, but existing batched methods remain synchronized: all requests in a batch share a single draft-verify schedule,
arxiv Sep 17
Multi-Agent Deep Reinforcement Learning for Maximal Extractable Value Allocation under Proposer-Builder Separation by Shengyu Chen, Hui Zhang, Junhuan Zhang :: SSRN
Develops MARL framework to analyze MEV allocation in decentralized exchange markets.
web Sep 16
EasyFashion: A Human-AI Co-Creation System for Personalized Fashion Design and Sewing Pattern Generation
Shows that multimodal (reference image + text) inputs outperform single-modality inputs for VLM-based agents by providing complementary semantic and structural grounding in garment tasks.
web Sep 16
Secure Selective Disclosure of Data for Digital Twinning Services | Arabian Journal for Science and Engineering | Springer Nature Link
States that digital twins serve as intermediaries between IoT devices and data consumers to improve availability and enforce access control.
web Sep 16
Internet of things - Wikipedia
Notes that the IoT term predates modern smartphones and catalogs overlapping concepts including CPS, pervasive computing, and industrial Internet.
web Sep 16
[2609.18027] Agents in the Scene: An Agentic Framework for Resource-Efficient Site-Specific Base Station Deployment
Presents an agentic framework that optimizes resource-efficient, site-specific base station deployment using autonomous agents.
web Sep 16
Reimagining research papers as interactive and reliable AI agents | Nature
Introduces Paper2Agent, an automated framework that converts research papers into interactive AI agents capable of answering questions and applying methods to new data.
web Sep 16
A Comprehensive Review of Generative Physical Artificial Intelligence
Summarizes performance gains and research directions in data-efficient, sim-to-real, and safety-aware embodied AI across autonomous vehicles, healthcare, and humanoid robotics.
web Sep 16
Turning scientific research papers into interactive AI agents | Nature
Describes Paper2Agent, an automated system that turns each paper into a virtual corresponding author agent for question answering and method application.
web Sep 16
[2609.17635] Physics-Constrained Digital Twins for Sensor Integrity in Urban Pedestrian Flow: Detecting Stealthy False Data Injection with Conformal Guarantees
Presents physics-constrained digital twins that detect stealthy false-data injection attacks on urban pedestrian-flow sensors with conformal prediction guarantees.
web Sep 15
World Models for Embodied Intelligence: From Plausible to Controllable to Actionable
Adds explicit long-term spatial memory to video world models, enabling persistent scene content across observations via geometry-grounded storage and retrieval.
web Sep 15
Validating Hybrid-State Cache Recovery for GLM-5.3-Flash with vLLM and LMCache
arXiv:2609.15030v1 Announce Type: new Abstract: External cache transfers can succeed while a hybrid language model resumes from an inconsistent state. We examine the full 45-layer GLM-5.3-Flash model, using the RedHatAI/ GLM-5.3-Flash-NVFP4 quantized checkpoint with vLLM and LMCache under four-way tensor parallelism. A complete-hit recovery mismatch restored state for the full prompt while the sc
arxiv Sep 15
Agentic Autoscaling through Worker-Pool Orchestration for LLM-driven Text Classification in Cloud Computing Environments
arXiv:2609.14898v1 Announce Type: new Abstract: The growing adoption of large language model (LLM)-based systems for large-scale text processing has created a critical need for dynamic autoscaling to manage high-latency, bursty, and computationally intensive workloads. This paper proposes an agentic autoscaling framework through worker-pool orchestration for LLM-driven text classification. The fr
arxiv Sep 15
CATS: A Carbon-Aware Task Simulator for Reducing AI Data Center Emissions
arXiv:2609.14775v1 Announce Type: new Abstract: The rapid rise of generative AI is accelerating cloud data center expansion, with electricity demand projected to double by 2026. Because carbon-intensity varies by more than 5.5x across grids and times of day, where and when inference tasks execute significantly affects operational emissions. We address this issue with three aspects in this paper.
arxiv Sep 15
TriCalRAG: A Three-Strategy, Retrieval-Augmented Benchmark for On-Premise LLM-Based Root Cause Analysis in AIOps
arXiv:2609.14762v1 Announce Type: new Abstract: Cloud-hosted large language models (LLMs) are increasingly used for root cause analysis (RCA) in AIOps pipelines, but they introduce data privacy risk, network latency, and per-query cost that scale poorly with production log volumes. We present TriCalRAG, a benchmark evaluating open-weight LLMs served locally via vLLM on a single high-memory workst
arxiv Sep 15
Stability-Aware Proactive Autoscaling Using a Double Deep Q-Network in Cloud Computing Environments
arXiv:2609.14894v1 Announce Type: new Abstract: Dynamic workloads and latency-sensitive applications require efficient autoscaling in cloud computing environments. However, most existing approaches rely on reactive mechanisms based on static thresholds, resulting in delayed responses and scaling oscillations under workload uncertainty. To address these limitations, we propose a double deep Q-Netw
arxiv Sep 15
[2609.16917] Multi-Agent Learning with Cooperation-Driven Optimization Dynamics
Examines cooperation-driven optimization dynamics as a mechanism for multi-agent learning convergence and coordination.
web Sep 15
Shared KV Caching for Replicated 27B Inference: Correctness Failures and Performance Boundaries
arXiv:2609.15021v1 Announce Type: new Abstract: Shared host-memory caching can avoid repeated prefill when a request moves between inference replicas. Its usefulness depends on both correct state transfer and lost prefix locality. We study two single-GPU 27B vLLM replicas sharing a 256 GiB LMCache pool. After adopting an existing packed-page patch, we isolate a raw-pointer fallback that omits the
arxiv Sep 15
SciSpace: 2026 Review for Researchers - The Effortless Academic
Presents SciSpace Deep Review, an AI-agent feature that automatically analyzes thousands of papers to produce a mini literature review from the top relevant results.
web Sep 14
RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments
Proposes Broad and Deep Recursive Self-exploration methods enabling RSIAgent to recursively improve open-source models past closed-source frontiers on OSWorld-v2 and Agent’s Last Exam.
web Sep 14
What is Agentic AI? - Agentic AI Explained - AWS
Outlines the definition, business value, and AWS implementation pathways for deploying Agentic AI systems.
web Sep 14
NFT-Based Reward Mechanisms: Sybil Farming, Vesting, and Stochastic Verification
We study NFT-based reward mechanisms in which a user can create multiple identities and submit fraudulent claims that mature a reward subject to vesting. We assume that the issuer stochastically verifies claims during the vesting period and that identities can be linked into clusters so that the detection of one identity submitting a fraudulent claim causes the whole cluster to be forfeited throug
arxiv Sep 11
Extreme-Scale Linear-Scaling Kohn-Sham DFT at 100 Million Atoms: Bridging Quantum Simulations and Experiments
Kohn-Sham density functional theory (DFT) remains the workhorse of ab initio materials simulation, yet cubic computational and quadratic memory scaling have confined calculations to a few hundred to thousands of atoms, spanning only nanometers, far below experimentally relevant length scales. We introduce XLSDFT, a linear-scaling DFT framework based on divide-and-conquer decomposition of the one-p
arxiv Sep 11
Dissecting GPU Utilization for LLM Inference on Nvidia Hopper
A single SM utilization percentage can make an LLM inference workload look compute-saturated while hiding how much useful work is being done. The problem is not that the counter is wrong, but that it collapses several different mechanisms into one number. This is most severe during decode, where each request contributes only one new token and dense projection GEMMs become small-row matrix multipli
arxiv Sep 11
Hidden in Rounds: Predicting the Time Cost of 802.11 Contention in Federated Learning
Federated learning over IEEE~802.11 shares the wireless channel among clients that send model updates. We use ns-3 to measure the frame-delivery ratio and saturation throughput for different client densities and offered loads. A separate FedAvg trainer uses the frame-delivery ratio as a first-order proxy for the update-admission probability and uses an equation to estimate communication time. The
arxiv Sep 11
4D Parallelism Unlocks Exascale Bayesian Neural Networks for High-Fidelity Atmospheric Modeling
We present BEAST, the first-ever Bayesian Swin Transformer for atmospheric forecasting on 0.25$^\circ$ global resolution able to accurately quantify both aleatoric and epistemic uncertainty. To overcome the associated computational bottlenecks, we devise an orthogonal 4D-parallelization scheme that introduces a unique domain-tensor-parallelism strategy and a novel uncertainty parallel method, enab
arxiv Sep 11
Hybrid Monitoring for Early Fault Detection in Cloud-Native 5G Systems
This paper presents the design implementation and evaluation of NetMon a hybrid network monitoring system designed for Kubernetes-based 5G packet core deployments specifically evaluated on Ericssons Access and Mobility Management Function AMF clusters NetMon combines eBPF-based passive kernel-level traffic observation with active TCP probing and centralized correlation to detect and localize netwo
arxiv Sep 11
Digital Twins and the Future of their Use Enabling Shift Left and Shift Right Cybersecurity Operations — Lacuna
Argues that the Digital Twin concept is the missing link for addressing scarce cybersecurity resources in operational technology domains.
web Sep 11
The Agent Incident Registry: Toward Preventing Repeated AI Agent Failures
Catalogs real-world AI-agent incidents, including production database deletion and data exfiltration via crafted prompts in Microsoft 365 Copilot.
web Sep 10
AI tools in evidence synthesis - Searching for Systematic Reviews & Evidence Synthesis - LibGuides at King’s College London
Demonstrates ChatGPT’s use across Boolean query generation, abstract screening, full-text extraction, and thematic analysis in systematic reviews.
web Sep 10
Agentic AI-Enabled Digital Twins for Intelligent Non-Destructive Testing of 3D-Printed Rehabilitation Equipment—A Narrative Review
Notes that incomplete or biased training data and added sensor complexity increase costs and cybersecurity demands when implementing autonomous digital twins.
web Sep 10
EMMI: Edge Multi-Modal Intelligence for Communication-Efficient MLLM Inference via Fused Representation Compression
Recent advances in multimodal large language mod- els (MLLMs) have opened new opportunities for edge intelligence by enabling reasoning across heterogeneous sensor modalities, such as vision, text, and telemetry data. However, deploying these capabilities on resource-constrained edge platforms remains challenging due to the substantial computational, memory, and communication demands of modern MLL
arxiv Sep 10
You've Got a BUD in Me: Authenticated Reads from Per-Block Write Logs
Blockchains usually pay for authenticated reads by maintaining a structure that spans the entire state. We show how validators can support historical membership and exclusion proofs by authenticating each block's writes instead. A Block Update Digest (BUD) commits a write log whose predecessor pointers link successive modifications of each key. A SuperBUD summarizes last writes over a window; an e
arxiv Sep 10
Phase-Decoupled, Model-Calibrated Power Control for Disaggregated LLM Serving
Datacenter GPU power is the binding constraint on LLM serving capacity, and production serving has shifted to prefill/decode (PD) disaggregation. Deploying NVIDIA's Max-Q inference profile on a disaggregated B200 system, we found its realized gain modest (+8.6% tokens/J), model-dependent, and carrying a mean end-to-end latency cost (+5.2%) that throughput-only evaluation does not surface; the prof
arxiv Sep 10
Online Treasure Hunt in Vertex-Permuted Dynamic Rings
We study the problem of treasure hunt by a group of $k \geq 1$ agents in vertex-permuted dynamic rings (VP). In this model, the $n$ vertices remain on a ring but are permuted at each time step. We first show that treasure hunt is impossible for any $k \leq n-3$ agents, if there are no restrictions on the sequence of permutations used in the dynamic ring. We then study the $VP(δ)$ setting, in which
arxiv Sep 10
A Model-Centric DevOps Architecture for DEVS-Based Digital Twin Simulation Services
Digital twin simulation models are evolved and redeployed like software, yet DEVS-based engines offer a sound formal basis with little support for versioning, automated validation, or continuous delivery in cloud-native environments, leaving model lifecycle management ad hoc in most deployments. This paper proposes a model-centric DevOps architecture for deploying DEVS-based digital twin simulatio
arxiv Sep 10
The Computing Channel: How Modulation Programs the Airwaves
Distributed computing and distributed artificial intelligence require frequent exchanges of intermediate results, although many applications need only an aggregate rather than messages from individual devices. Conventional systems recover each message before computing the aggregate, whereas over-the-air computation (OAC) exploits simultaneous transmission to obtain it directly. However, dominant O
arxiv Sep 10
Rethinking Sparse Formats for RISC-V: A Hierarchical Approach to High-Performance SpMV
The sparse matrix-vector multiplication (SpMV) algorithm is a fundamental computational kernel of linear algebra and serves as a building block for numerous applications, primarily iterative solvers for systems of linear equations used in scientific and engineering simulations. This paper compares vectorized implementations of the SpMV algorithm across eight established sparse matrix storage forma
arxiv Sep 10
GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph Replay
Counterfactual regret minimization (CFR) is one of the few large numerical workloads that still runs faster on CPUs than on GPUs. Each iteration sweeps a game tree with up to billions of states in millions of small, interdependent gather and scatter steps issued through a generic tree interface. On a GPU every kernel finishes in microseconds, so kernel launches and framework dispatch dominate the
arxiv Sep 10
Entwine: Coordinating Tiled Computation and Fine-Grained Communication across GPUs
Modern high-performance GPU computations partition tensors into tiles to exploit data reuse and parallelism. Individual tile computations complete earlier than the full tensor computation, creating opportunities to overlap computation and communication. However, a mismatch between computation and communication progress can limit these opportunities. Communication stalls when no data is ready, and
arxiv Sep 10
Domain-Specific Hallucination Detection in Large Language Models
Presents a multi-signal hallucination detection pipeline (DeBERTa-v3 + MC Dropout + temperature calibration) achieving F1=0.915 and AUROC=0.977 on HaluEval.
arxiv Sep 10
From Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge
Uses layer-wise hidden-state interventions to quantify how LLMs (Qwen, Llama, Gemma) shift reliance between query-routing information and target knowledge during question answering.
arxiv Sep 10
Biology-in-the-loop: Amortized Adaptive Hit Discovery in CRISPR Screens
Introduces AssayBench-Loop, a large-scale benchmark for sequential, budget-constrained experiment selection in adaptive biological hit discovery such as CRISPR screening.
arxiv Sep 10
Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model
Demonstrates that visually grounded token embeddings (via ostension) in a small DeBERTa model trained on 10M words produce a measurable, persistent imprint through the end of training.
arxiv Sep 10
The Agent Incident Registry: Toward Preventing Repeated AI Agent Failures
Catalogs recent AI-agent incidents including a Replit coding agent deleting a production database and Copilot data exfiltration via crafted email.
web Sep 10
Can Edge-Deployable Vision-Language Models Identify Species?
Evaluates small VLMs (Qwen3-VL 2B/4B/8B, Gemma3 4B) against BioCLIP on a 96-species camera-trap identification task to test genuine taxonomic knowledge in deployment-relevant 2-8B edge models.
arxiv Sep 10
[2609.11018] Defining AI Agents: A Compendium of Criteria, Metrics, and Benchmarks
Compendium that catalogs criteria, metrics, and benchmarks used to define and evaluate AI agents across the literature.
web Sep 10