ReadWhen Cooperation Must Change: Semantic Strategy Unlearning in Multi-Agent Reinforcement Learning#Reinforcement learning#Multi Agent SystemsarXiv: Artificial IntelligencearticleNov 16, 2026
ReadWhat’s Fixed and Improved in PyCharm 2026.3#PyCharm#Static code analysisJetBrainsreleaseNov 13, 2026
ReadLet's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification#llm-reasoning#AI ChatarXiv: Artificial IntelligencearticleNov 13, 2026
ReadOverServe: Resource Amplification Attacks on SaaS Agents via Tool--Prompt Co-Design#ai-assisted attacks#AI AgentarXiv: Artificial IntelligencearticleNov 13, 2026
ReadMARS: Towards High Goodput and Low KV Thrashing in Agent Serving under GPU Memory Constraints#vllm#CachearXiv: Distributed ComputingarticleNov 13, 2026
ReadSwarmSafe-Delta: Isolating Message Effects on LLM Agent Safety#Multi Agent Systems#agent to agent communicationarXiv: Artificial IntelligencearticleNov 13, 2026
ReadMulti-Task Self-Evolving Harnesses with the Agent as Its Own Optimizer#Agent Harness#Multi-step AI processesarXiv: Artificial IntelligencearticleNov 13, 2026
ReadEfficient Alternating Minimization with Applications to Weighted Low Rank Approximation#Machine learningarXiv: Machine LearningarticleNov 13, 2026
ReadLow Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time#AlgorithmsarXiv: Machine LearningarticleNov 13, 2026
ReadOmni-JEV: Text and Dual-Stream Speech Decisions#Conversational AI#Reinforcement learningarXiv: Machine LearningarticleNov 11, 2026
ReadModel-Free Runtime Measurement of Task-Relevant Information#ai observability#rlvrarXiv: Artificial IntelligencearticleNov 11, 2026
ReadUGG: Unified Generative Geometry Model#Generative AI#multimodal-aiarXiv: Machine LearningarticleNov 11, 2026
ReadReview the Episodes, Refine the Lessons: Simple Memory Evolution for Embodied Agents#llm-reasoning#Machine PerceptionarXiv: Artificial IntelligencearticleNov 10, 2026
ReadLearning inexact alternating minimization for convex problems with quadratic coupling#Machine learning#Fine-tuningarXiv: Machine LearningarticleNov 10, 2026
ReadCulturalCrosswords: A Multilingual Benchmark comprised of Answer Constraints and Grid Completion#Benchmark#Machine learningarXiv: Artificial IntelligencearticleNov 10, 2026
ReadSame Error, Different Recovery: How Delivery Changes LLM Agent Behavior#Multi-step AI processes#Error HandlingarXiv: Artificial IntelligencearticleNov 10, 2026
ReadText Grouping Changes Completion-Time Comparisons in Long-Form Simultaneous Speech Translation#machine-translation#Speech ProcessingarXiv: Artificial IntelligencearticleNov 10, 2026
ReadShortcuts and Boundaries: Verifiable RL Misalignment and Contextual Safety Learning#Reinforcement learning#ai alignmentarXiv: Artificial IntelligencearticleNov 10, 2026
ReadCARE-PO: Controllable Tool-Call Efficiency for LLM Agents#grpo#Multi-step AI processesarXiv: Artificial IntelligencearticleNov 10, 2026
ReadJoi-Bench-Task: Benchmarking Task Coordination in Full-duplex Voice Agents through Interactive Simulation#Conversational AI#Interactive AI SystemsarXiv: Artificial IntelligencearticleNov 10, 2026
ReadHeteroTask: Multi-Variant Task Scheduling and Execution on Distributed Heterogeneous Clusters#Distributed Systems & Parallel Computing#schedulingarXiv: Distributed ComputingnewsNov 10, 2026
ReadAuthorization Drift in LLM Agents: Evaluating Boundary Compliance in Multi-Step Tool Use#LLM security#AuthorizationarXiv: Cryptography and SecurityarticleNov 9, 2026
ReadVLA Handover: Failure-Prediction-Based Switching from On-Robot to Server VLA Models#Isaac#smolvlaarXiv: Machine LearningarticleNov 9, 2026
ReadSelf-Programmed Execution for Language-Model Agents#Agent Harness#Large Language ModelarXiv: Artificial IntelligencearticleNov 9, 2026