Key papers

• AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities (2026)
  Zichen Ding et al.
  12.21
• Infinite Worlds with Versatile Interactions (2026)
  Zelin Gao et al.
  10.90
• Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning (2026)
  Jian Hu et al.
  9.05
• Understanding Reasoning from Pretraining to Post-Training (2026)
  Jingyan Shen et al.
  7.92
• Control Laguerre Tessellation: Semi-discrete Optimal Transport Over Control Systems (2026)
  Ripon C. Sarker et al.
  5.44
• Living-Harness Is an Interactive-Agent Evolver (2026)
  Yuetian Du et al.
  5.44
• Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants (2026)
  Zijian Xu et al.
  5.44
• AgentMap: Joint Equivalence and Subsumption Discovery for Ontology Matching (2026)
  Yiping Song et al.
  5.44
• ToolGuardian: Declarative Security for AI Agent-Tool Interactions (2026)
  Arun Ravindran et al.
  4.95
• J-CoT: Chain-of-Thought in J-Space (2026)
  Junde Wu et al.
  4.95
• One Hand Watches The Other: Dynamic Multi-Agent Cooperation for Sample-Efficient Bimanual Manipulation in Dynamic Environments (2026)
  Jan Ole von Hartz et al.
  4.95
• Probabilistic Extension of Neuro-Symbolic AGI Robots based on Belnap's Typed Intensional FOL (2026)
  Zoran Majkic
  4.33
• DevicesWorld: Benchmarking Cross-Device Agents in Heterogeneous Environments (2026)
  Huatao Li et al.
  4.33
• Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling (2026)
  Xixuan Hao et al.
  4.33
• Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3? (2026)
  Sergey Rodionov
  4.33
• CoWeaver: A Bi-directional, Learnable and Explainable Matching Engine for Mixed Human-Agent Science Collaboration (2026)
  Jiayao Gu et al.
  4.33
• Hard Rules, Soft Preferences: Bridging Reasoning, Learning, and Optimization for Personalized Packing Checklist Generation (2026)
  Himel Dev et al.
  4.33
• Think at 5 Hz, Act at 20 Hz: Asynchronous Fast-Slow Vision-Language-Action Inference for Closed-Loop Driving (2026)
  Yun Li et al.
  4.33
• Presentation, Not Mechanism: A Render Confound in Deprecation-Aware Memory Evaluation (2026)
  Zhaoyang Jiang et al.
  4.33
• Engineering Trustworthy Agentic AI for Critical Systems (2026)
  Omar Al-Refai et al.
  4.33
• Coupled Hierarchical Search over Topology and Execution for Agentic Workflow Synthesis (2026)
  Dong Li et al.
  4.33
• Toward User-Conditioned Evaluation of Personal LLM Agents under Temporal Interventions (2026)
  Pin Qian et al.
  4.33
• TRW: TRACE-RealWorld---An Auditable Consistency Contract for World Models as Materialized Views (2026)
  Edward Y. Chang
  4.33
• Multi-Agent Debate and Visual Information Extraction for SeePhys Pro: A 1st-Place Technical Report from ICML 2026 AI4Math Track 3 Challenge (2026)
  Jiseok Kwak et al.
  4.33
• A Self-Calibrating Agentic AI Framework for Autonomous Edge Resource Allocation (2026)
  Fin Gentzen et al.
  4.33
• TRACE-ROUTER: Task-Consistent and Adaptive Online Routing for Agentic AI (2026)
  Ritik Raj et al.
  4.33
• An Unofficial FastLAS Tutorial: A Programmer's Guide (2026)
  Fabio Aurelio D'Asaro
  4.33
• Where Is the Cost of Third-Party API Routers in Agentic Software Development? (2026)
  Donghao Fu et al.
  4.33
• LabRobFail: A Benchmark for Robotic Failure Analysis in Chemical Self-driving Laboratory (2026)
  Haobo Wang et al.
  4.33
• Extremal Chowla sets and their linear analogues: A human-AI mathematical investigation using Co-Scientist (2026)
  Mohsen Aliabadi et al.
  4.33
• PLATO: Pointer Learner for Agent and Task Openness (2026)
  Alireza Saleh Abadi et al.
  4.33
• Interpretable GOHR Agents via Sparse Autoencoders (2026)
  Shiwei Tan et al.
  4.33
• Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales (2026)
  Genliang Zhu (Accentrust et al.
  4.33
• Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction (2026)
  Xinyi Hong et al.
  4.33
• Interactive Reward Agent: GUI Task Evaluation via Environment-State Verification (2026)
  Chenrui Shi et al.
  4.33
• Sim2Win: A Team-Agnostic, Event-Based Pre-Match Outcome Prediction and Tactical Profiling System for Football (2026)
  Mouad Zemzoumi et al.
  4.33
• Harnessing Large Language Models for Intelligent Resource Allocation in the Internet of Everything (2026)
  Haijun Zhang et al.
  4.33
• Process Reward Informed Tree Rollout for Effective Multi-Turn RL (2026)
  Xintong Li et al.
  3.45
• Decentralized Online Riemannian Optimization for Strongly Geodesically Convex Functions (2026)
  Zhanyuan Cai et al.
  3.45
• FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills (2026)
  Zeyu Ren et al.
  3.45
• From Isolated Tasks to Structured Capabilities: A Multilayer Taxonomy for Large Language Models (2026)
  Shixin Fang (Fudan University) et al.
  3.45
• ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory (2026)
  Jiayi Tian et al.
  1.94
• BrainPilot: Automating Brain Discovery with Agentic Research (2026)
  Haoxuan Li et al.
  1.94
• Fantastic Adaptive Taxonomies and How to Use Them (2026)
  Mert Cemri et al.
  1.94
• The Cost of Knowing: A Resource-Aware Protocol for Benchmarking Hallucination Beyond Static Leaderboards (2026)
  Keyu Li et al.
  1.94
• Agent-UCT: Upper Confidence Bounds Applied to Trees for Agentic Workflow Optimization with Cost-Awareness (2026)
  Yang Li et al.
  1.94
• Multi-Agent Planning with Spatio-Temporal and Topological Constraints using STL-GO (2026)
  Sheryl Paul et al.
  1.94
• Adjudicated Captioning: Multi-Agent Alignment Scoring and Consensus-Distilled Beam Arbitration for Strict Zero-Shot Image Captioning (2026)
  Duy Tran Thanh et al.
  1.94
• Autonomous Repair for Multi-Agent Systems via Monte-Carlo Tree Search (2026)
  Hanxiao Lu et al.
  1.94
• SeekBrain: An Autonomous Multi-Agent System for Accelerating Neuroscience Discovery (2026)
  Jiamin Wu et al.
  1.94
• Beyond Component Testing: Validating Agentic AI Systems (2026)
  Fabio Orazio Mirto et al.
  1.94
• Transcript-Managed Transformers: Monotone Multi-Agent Collapse and Universality with Two Pop-Enabled Transcripts (2026)
  Sergey Salishev
  1.94
• A Multi-Agent System for Motor Design Optimization via an FEA-AI Hybrid Approach (2026)
  Jinseong Han et al.
  1.89
• MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination (2026)
  Joss Armstrong
  1.83
• MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing (2026)
  Han Chen et al.
  1.83
• SCMAPR: Self-Correcting Multi-Agent Prompt Refinement for Complex-Scenario Text-to-Video Generation (2026)
  Chengyi Yang et al.
  1.78
• Co-Director: Agentic Generative Video Storytelling (2026)
  Yale Song et al.
  1.78
• AIvilization v0: Toward Large-Scale Artificial Social Simulation with a Unified Agent Architecture and Adaptive Agent Profiles (2026)
  Wenkai Fan et al.
  1.67
• The Practicality of Normalizing Flow Test-Time Training in Bayesian Inference for Agent-Based Models (2026)
  Junyao Zhang et al.
  1.61
• Complementary Characterization of Agent-Based Models via Computational Mechanics and Diffusion Models (2025)
  Roberto Garrone
  1.56