{"total":27,"rows":[{"id":"2606.29537","title":"OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks","created":"2026-06-28","cited_by_count":40,"area":"agents"},{"id":"2605.28424","title":"Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning","created":"2026-05-27","cited_by_count":9,"area":"agents"},{"id":"2606.11435","title":"Agent Skill Evaluation and Evolution: Frameworks and Benchmarks","created":"2026-06-09","cited_by_count":8,"area":"agents"},{"id":"2606.16748","title":"MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents","created":"2026-06-15","cited_by_count":7,"area":"agents"},{"id":"2607.22368","title":"Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI","created":"2026-07-24","cited_by_count":6,"area":"agents"},{"id":"2608.15127","title":"From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems","created":"2026-08-15","cited_by_count":5,"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":"2608.13505","title":"Intern-S2-Preview: Scientific Agentic Foundation Model","created":"2026-08-13","cited_by_count":4,"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":"2606.23654","title":"EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions","created":"2026-06-22","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":"2609.25611","title":"Qwen3.8-Omni: Towards Native Omni-Modal Agents","created":"2026-09-22","cited_by_count":2,"area":"agents"},{"id":"2607.06008","title":"PolyWorkBench: Benchmarking LLM Agents for Cross-Lingual Long-Horizon Workflows","created":"2026-07-07","cited_by_count":1,"area":"agents"},{"id":"2607.28037","title":"ClawTrack: Towards Trace-Level Evaluation and Improvement of Real-World Autonomous Agents","created":"2026-07-30","cited_by_count":1,"area":"agents"},{"id":"2608.20485","title":"Terminal Agents: A Survey of AI Agents in Command-Line Environments","created":"2026-08-20","cited_by_count":1,"area":"agents"},{"id":"2605.27492","title":"Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems","created":"2026-05-26","cited_by_count":0,"area":"agents"},{"id":"2607.16610","title":"Just A Rather Very Intelligent Spoken Agent","created":"2026-07-18","cited_by_count":0,"area":"agents"},{"id":"2608.20566","title":"AgentDecarbonizer: Carbon-Aware Execution for AI Agents","created":"2026-08-20","cited_by_count":0,"area":"agents"},{"id":"2609.15396","title":"SkillLift: Learning Dense Rubrics from Sparse Oracles for Efficient Skill Evolution","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.33295","title":"TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.35807","title":"Environment Steering: Using Data Flow Control to Improve Agent Utility and Safety","created":"2026-09-19","cited_by_count":0,"area":"agents"},{"id":"2609.38867","title":"Talk2Agent: Benchmarking Voice Interfaces for Text Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2609.40284","title":"cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.09872","title":"LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.09944","title":"AgentTime: Can Agents Estimate and Control Their Own Runtime?","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.14118","title":"ClawLoop: Self-Improving Agents via Harness-Native Training Loop","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.17816","title":"Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}