{"total":284,"rows":[{"id":"2604.25850","title":"Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses","created":"2026-04-28","cited_by_count":142,"area":"agents"},{"id":"2607.24653","title":"Kimi K3: Open Frontier Intelligence","created":"2026-07-27","cited_by_count":138,"area":"agents"},{"id":"2605.10912","title":"WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation","created":"2026-05-11","cited_by_count":37,"area":"agents"},{"id":"2605.23950","title":"Stop Comparing LLM Agents Without Disclosing the Harness","created":"2026-05-07","cited_by_count":34,"area":"agents"},{"id":"2606.01139","title":"SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision","created":"2026-05-31","cited_by_count":30,"area":"agents"},{"id":"2605.21384","title":"SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents","created":"2026-05-20","cited_by_count":28,"area":"agents"},{"id":"2605.22166","title":"Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents","created":"2026-05-21","cited_by_count":27,"area":"agents"},{"id":"2606.17573","title":"Cordon: Semantic Transactions for Tool-Using LLM Agents","created":"2026-06-16","cited_by_count":22,"area":"agents"},{"id":"2606.17861","title":"GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?","created":"2026-06-16","cited_by_count":22,"area":"agents"},{"id":"2606.30616","title":"Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent","created":"2026-06-29","cited_by_count":22,"area":"agents"},{"id":"2605.02240","title":"PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments","created":"2026-05-04","cited_by_count":21,"area":"agents"},{"id":"2607.09996","title":"Who&When Pro: Can LLMs Really Attribute Failures in AI Agents?","created":"2026-07-10","cited_by_count":18,"area":"agents"},{"id":"2608.02276","title":"Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories","created":"2026-08-03","cited_by_count":16,"area":"agents"},{"id":"2605.17637","title":"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games","created":"2026-05-17","cited_by_count":12,"area":"agents"},{"id":"2607.01071","title":"MemSyco-Bench: Benchmarking Sycophancy in Agent Memory","created":"2026-07-01","cited_by_count":12,"area":"agents"},{"id":"2607.10891","title":"SETA: Scaling Environments for Terminal Agents","created":"2026-07-12","cited_by_count":12,"area":"agents"},{"id":"2605.08715","title":"AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems","created":"2026-05-09","cited_by_count":11,"area":"agents"},{"id":"2605.30248","title":"GenClaw: Code-Driven Agentic Image Generation","created":"2026-05-28","cited_by_count":11,"area":"agents"},{"id":"2606.11559","title":"HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation","created":"2026-06-10","cited_by_count":11,"area":"agents"},{"id":"2608.09096","title":"Evo-Bench: Can Language Models Improve Agent Harness?","created":"2026-08-10","cited_by_count":11,"area":"agents"},{"id":"2606.20659","title":"Skill Coverage: A Test Adequacy Metric for Agent Skills","created":"2026-06-09","cited_by_count":8,"area":"agents"},{"id":"2606.23416","title":"Detecting Malicious Agent Skills in the Wild using Attention","created":"2026-06-22","cited_by_count":8,"area":"agents"},{"id":"2607.04425","title":"UI-MOPD: Multi-Platform On-Policy Distillation for Unified GUI Agents","created":"2026-07-05","cited_by_count":8,"area":"agents"},{"id":"2608.01679","title":"When Memory Becomes Authority: Benchmarking Authority Collapse at the Memory Consolidation Boundary","created":"2026-08-03","cited_by_count":8,"area":"agents"},{"id":"2605.13950","title":"Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction","created":"2026-05-13","cited_by_count":7,"area":"agents"},{"id":"2605.30883","title":"TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking","created":"2026-05-29","cited_by_count":7,"area":"agents"},{"id":"2606.03565","title":"Skill Is Not Document: Query-Conditioned Compatibility for LLM Agent Skill Routing","created":"2026-06-02","cited_by_count":7,"area":"agents"},{"id":"2606.25819","title":"Beyond Function Calling: Benchmarking Tool-Using Agents under Tool-Environment Unreliability","created":"2026-06-24","cited_by_count":7,"area":"agents"},{"id":"2607.08938","title":"Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation","created":"2026-07-09","cited_by_count":7,"area":"agents"},{"id":"2607.12893","title":"MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations","created":"2026-07-14","cited_by_count":7,"area":"agents"},{"id":"2607.14186","title":"NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs","created":"2026-07-15","cited_by_count":7,"area":"agents"},{"id":"2608.01837","title":"PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning","created":"2026-08-03","cited_by_count":7,"area":"agents"},{"id":"2608.27311","title":"Verify Smarter, Evolve Further: Efficient Harness Evolution through Behavior-Aware Verification","created":"2026-08-27","cited_by_count":7,"area":"agents"},{"id":"2606.14302","title":"Retrospective Progress-Aware Self-Refinement for LLM Agent Training","created":"2026-06-12","cited_by_count":6,"area":"agents"},{"id":"2605.10779","title":"LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments","created":"2026-05-11","cited_by_count":5,"area":"agents"},{"id":"2605.25200","title":"GroupTravelBench: Benchmarking LLM Agents on Multi-Person Travel Planning","created":"2026-05-24","cited_by_count":5,"area":"agents"},{"id":"2605.28721","title":"LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know?","created":"2026-05-27","cited_by_count":5,"area":"agents"},{"id":"2606.18837","title":"Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems","created":"2026-06-17","cited_by_count":5,"area":"agents"},{"id":"2607.17100","title":"Auto Research for Materials: Auditable AI-Scientist Workflows with Held-Out Transfer","created":"2026-07-19","cited_by_count":5,"area":"agents"},{"id":"2608.07645","title":"Mendel G\\\"odel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution","created":"2026-08-07","cited_by_count":5,"area":"agents"},{"id":"2609.24974","title":"Harness-Zero: Harness Distillation via Agent-as-Harness","created":"2026-09-21","cited_by_count":5,"area":"agents"},{"id":"2605.07039","title":"PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents","created":"2026-05-07","cited_by_count":4,"area":"agents"},{"id":"2605.17526","title":"SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering","created":"2026-05-17","cited_by_count":4,"area":"agents"},{"id":"2605.23657","title":"OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents","created":"2026-05-22","cited_by_count":4,"area":"agents"},{"id":"2605.30434","title":"LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2606.16591","title":"SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents","created":"2026-06-15","cited_by_count":4,"area":"agents"},{"id":"2607.02911","title":"CoACT: Action-Preserving Observation Compression for Coding Agents","created":"2026-07-03","cited_by_count":4,"area":"agents"},{"id":"2607.06273","title":"AgentTether: Graph-Guided Diagnosis and Runtime Intervention for Reliable LLM Agent Operation","created":"2026-07-07","cited_by_count":4,"area":"agents"},{"id":"2607.09375","title":"Mach-Mind-4-Flash Technical Report","created":"2026-07-10","cited_by_count":4,"area":"agents"},{"id":"2607.20891","title":"Is Deep Research Reliable? Misleading Knowledge Induces False Conclusions","created":"2026-07-23","cited_by_count":4,"area":"agents"},{"id":"2608.05013","title":"OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents","created":"2026-08-04","cited_by_count":4,"area":"agents"},{"id":"2608.13505","title":"Intern-S2-Preview: Scientific Agentic Foundation Model","created":"2026-08-13","cited_by_count":4,"area":"agents"},{"id":"2605.08756","title":"AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design","created":"2026-05-09","cited_by_count":3,"area":"agents"},{"id":"2605.16508","title":"The Scaling Laws of Skills in LLM Agent Systems","created":"2026-05-15","cited_by_count":3,"area":"agents"},{"id":"2605.23986","title":"MemForest: An Efficient Agent Memory System with Hierarchical Temporal Indexing","created":"2026-05-16","cited_by_count":3,"area":"agents"},{"id":"2606.02404","title":"K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts","created":"2026-06-01","cited_by_count":3,"area":"agents"},{"id":"2606.03239","title":"ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agents","created":"2026-06-02","cited_by_count":3,"area":"agents"},{"id":"2606.07462","title":"Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle","created":"2026-06-05","cited_by_count":3,"area":"agents"},{"id":"2606.13120","title":"EvoBrowseComp: Benchmarking Search Agents on Evolving Knowledge","created":"2026-06-11","cited_by_count":3,"area":"agents"},{"id":"2606.22673","title":"AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent","created":"2026-06-21","cited_by_count":3,"area":"agents"},{"id":"2607.20062","title":"Solar Open 2 Technical Report","created":"2026-07-22","cited_by_count":3,"area":"agents"},{"id":"2607.24850","title":"SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task","created":"2026-07-25","cited_by_count":3,"area":"agents"},{"id":"2607.29320","title":"MAGA: Multi-Platform Self-Fusion of GUI Agents via Structured Action Distillation","created":"2026-07-31","cited_by_count":3,"area":"agents"},{"id":"2608.01149","title":"PATH-Bench: Path-Dependent Evaluation of Lifelong Agents","created":"2026-08-02","cited_by_count":3,"area":"agents"},{"id":"2608.02287","title":"SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation","created":"2026-08-03","cited_by_count":3,"area":"agents"},{"id":"2608.19741","title":"One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows","created":"2026-08-20","cited_by_count":3,"area":"agents"},{"id":"2608.25500","title":"CaSKG: Counterfactual-Causal Skill Graphs for Scalable Agent Skill Retrieval","created":"2026-08-26","cited_by_count":3,"area":"agents"},{"id":"2608.25776","title":"EVOMAL: Self-Poisoning in Self-Evolving Coding Agents","created":"2026-08-26","cited_by_count":3,"area":"agents"},{"id":"2609.11977","title":"Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work","created":"2026-09-04","cited_by_count":3,"area":"agents"},{"id":"2609.20784","title":"RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning","created":"2026-09-17","cited_by_count":3,"area":"agents"},{"id":"2605.07840","title":"RelAgent: LLM Agents as Data Scientists for Relational Learning","created":"2026-05-08","cited_by_count":2,"area":"agents"},{"id":"2605.08761","title":"Beyond the All-in-One Agent: Benchmarking Role-Specialized Multi-Agent Collaboration in Enterprise Workflows","created":"2026-05-09","cited_by_count":2,"area":"agents"},{"id":"2605.22321","title":"ASEval: Automated Trajectory-Level Security Testing for Autonomous Agents","created":"2026-05-21","cited_by_count":2,"area":"agents"},{"id":"2605.28003","title":"ResearchMath-14K: Scaling Research-Level Mathematics via Agents","created":"2026-05-27","cited_by_count":2,"area":"agents"},{"id":"2605.28108","title":"Ask Now, Use Later: Benchmarking the Proactivity Gap in Long-Lived LLM Agents","created":"2026-05-27","cited_by_count":2,"area":"agents"},{"id":"2605.29893","title":"Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories","created":"2026-05-28","cited_by_count":2,"area":"agents"},{"id":"2606.03083","title":"DELTAMEM: Incremental Experience Memory for LLM Agents via Residual Trees","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2606.05828","title":"Statistical Priors for Implicit Preferences: Decoupling Skill Selection as a Local Harness in Personal Agents","created":"2026-06-04","cited_by_count":2,"area":"agents"},{"id":"2606.06416","title":"Unsupervised Skill Discovery for Agentic Data Analysis","created":"2026-06-04","cited_by_count":2,"area":"agents"},{"id":"2606.15345","title":"Beyond Monolingual Deep Research: Evaluating Agents and Retrievers with Cross-Lingual BrowseComp-Plus","created":"2026-06-13","cited_by_count":2,"area":"agents"},{"id":"2606.18237","title":"ReproRepo: Scaling Reproducibility Audits with GitHub Repository Issues","created":"2026-06-16","cited_by_count":2,"area":"agents"},{"id":"2606.20661","title":"From Knowing to Acting: Benchmarking Self-Awareness Capability of LLM Agents","created":"2026-06-09","cited_by_count":2,"area":"agents"},{"id":"2606.23991","title":"Critique of Agent Model","created":"2026-06-22","cited_by_count":2,"area":"agents"},{"id":"2607.08565","title":"SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling","created":"2026-07-09","cited_by_count":2,"area":"agents"},{"id":"2607.11698","title":"Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming","created":"2026-07-13","cited_by_count":2,"area":"agents"},{"id":"2607.13705","title":"AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities","created":"2026-07-15","cited_by_count":2,"area":"agents"},{"id":"2607.18084","title":"WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting","created":"2026-07-20","cited_by_count":2,"area":"agents"},{"id":"2607.27155","title":"OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding","created":"2026-07-29","cited_by_count":2,"area":"agents"},{"id":"2608.04192","title":"Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills","created":"2026-08-04","cited_by_count":2,"area":"agents"},{"id":"2608.04934","title":"State2State: Environment-Derived Mid-Training for LLM Agents","created":"2026-08-05","cited_by_count":2,"area":"agents"},{"id":"2608.06485","title":"Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events","created":"2026-08-06","cited_by_count":2,"area":"agents"},{"id":"2608.17597","title":"HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety","created":"2026-08-18","cited_by_count":2,"area":"agents"},{"id":"2608.21027","title":"Don't Solve, Just Compare: Tiny Advisors for Runtime Intervention in LLM Agents","created":"2026-08-21","cited_by_count":2,"area":"agents"},{"id":"2608.23283","title":"Apodex 1.1: Scaling Agentic Intelligence for Complex Work","created":"2026-08-24","cited_by_count":2,"area":"agents"},{"id":"2608.24509","title":"PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents","created":"2026-08-25","cited_by_count":2,"area":"agents"},{"id":"2608.26372","title":"Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2609.12818","title":"Online Video Agent Harness for Long Video Understanding","created":"2026-09-11","cited_by_count":2,"area":"agents"},{"id":"2605.01920","title":"A Language for Describing Agentic LLM Contexts","created":"2026-05-03","cited_by_count":1,"area":"agents"},{"id":"2605.27605","title":"Laguna M.1/XS.2 Technical Report","created":"2026-05-26","cited_by_count":1,"area":"agents"},{"id":"2605.27882","title":"VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild","created":"2026-05-27","cited_by_count":1,"area":"agents"}],"next_cursor":"100"}