Key papers

• EASYTOOL: Enhancing Llm-based Agents With Concise Tool Instruction (2024)
  Siyu Yuan, Kaitao Song, Jiangjie Chen, et al.
  16.88
• Qwen-AgentWorld: Language World Models for General Agents (2026)
  Yuxin Zuo et al.
  14.85
• Deep Research Agents: A Systematic Examination And Roadmap (2025)
  Yuxuan Huang et al.
  13.91
• UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks (2026)
  Zhekai Chen et al.
  13.35
• OpenComputer: Verifiable Software Worlds for Computer-Use Agents (2026)
  Jinbiao Wei et al.
  12.83
• MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research (2026)
  Dingbang Wu et al.
  12.79
• Understanding The Weakness Of Large Language Model Agents Within A Complex Android Environment (2024)
  Mingzhe Xing, Rongkai Zhang, Hui Xue, et al.
  12.57
• K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts (2026)
  Nahyun Lee et al.
  12.51
• AI Research Agents Narrow Scientific Exploration (2026)
  Yixuan Tang et al.
  12.14
• GrepSeek: Training Search Agents for Direct Corpus Interaction (2026)
  Alireza Salemi et al.
  11.95
• Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents (2026)
  Suji Kim et al.
  11.92
• AgenticDataBench: A Comprehensive Benchmark for Data Agents (2026)
  Zhaoyan Sun et al.
  11.78
• Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism (2026)
  Haoxiang Zhang et al.
  11.32
• Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses (2026)
  Pengcheng Jiang et al.
  10.97
• Swe-agent: Agent-computer Interfaces Enable Automated Software Engineering (2024)
  John Yang, Carlos E. Jimenez, Alexander Wettig, et al.
  10.85
• CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents (2026)
  Bowen Wang et al.
  10.76
• NVIDIA-labs OO Agents: Native Python Object-Oriented Agents (2026)
  Paul Furgale et al.
  10.76
• MARS: Modular Agent with Reflective Search for Automated AI Research (2026)
  Jiefeng Chen et al.
  10.74
• QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks (2026)
  Jian Xie et al.
  10.72
• Benchmark Test-Time Scaling of General LLM Agents (2026)
  Xiaochuan Li et al.
  10.20
• QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents (2026)
  Ye Yuan et al.
  10.04
• Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability (2026)
  Sizhe Zhou et al.
  9.91
• LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know? (2026)
  HuiMing Fan et al.
  9.89
• AI agent in healthcare: applications, evaluations, and future directions (2026)
  Lina Zhao et al.
  9.70
• Data Interpreter: An LLM Agent For Data Science (2024)
  Sirui Hong, Yizhang Lin, Bang Liu, et al.
  9.66
• SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents (2026)
  Wenxuan Wang et al.
  9.62
• Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills (2026)
  Chuan Xiao et al.
  9.62
• CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks? (2026)
  Yuxin Zhang et al.
  9.62
• LLM Agents Making Agent Tools (2025)
  Georg Wölflein, Dyke Ferber, Daniel Truhn, et al.
  9.62
• Agent-pro: Learning To Evolve Via Policy-level Reflection And Optimization (2024)
  Wenqi Zhang, Ke Tang, Hai Wu, et al.
  9.59
• VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions (2026)
  Yuxin Chen et al.
  9.56
• Mobile-agent-v3.5: Multi-platform Fundamental GUI Agents (2026)
  Haiyang Xu, Xi Zhang, Haowei Liu, et al.
  9.54
• RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents (2025)
  Zijing Zhang et al.
  9.53
• Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents (2026)
  Yifan Wu et al.
  9.48
• OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents (2026)
  Rui Yang et al.
  9.43
• Edge Large AI Model Agent-Empowered Cognitive Multimodal Semantic Communication (2026)
  Y. Sun et al.
  9.39
• TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents (2026)
  Hang Yan et al.
  9.37
• Anticipate and Learn: Unleashing Idle-Time Compute in Proactive Agents (2026)
  Haoyi Hu et al.
  9.30
• DSWorld: A Data Science World Model for Efficient Autonomous Agents (2026)
  Zherui Yang et al.
  9.05
• A Survey On The Optimization Of Large Language Model-based Agents (2025)
  Shangheng Du, Jiabao Zhao, Jinxin Shi, et al.
  9.04
• Tptu-v2: Boosting Task Planning And Tool Usage Of Large Language Model-based Agents In Real-world Systems (2023)
  Yilun Kong, Jingqing Ruan, Yihong Chen, et al.
  9.03
• EvoBrowseComp: Benchmarking Search Agents on Evolving Knowledge (2026)
  Yunhan Wang et al.
  8.84
• ORCA-bench: How Ready Are Language Model Agents for Oncall? (2026)
  Albert Gong et al.
  8.66
• Mobile-bench: An Evaluation Benchmark For Llm-based Mobile Agents (2024)
  Shihan Deng, Weikai Xu, Hongda Sun, et al.
  8.35
• Agent Lumos: Unified And Modular Training For Open-source Language Agents (2023)
  da Yin, Faeze Brahman, Abhilasha Ravichander, et al.
  8.35
• Harness-G: A Graph-Structured Harness for Search Agents (2026)
  Yanning Hou et al.
  7.93
• OpenForgeRL: Train Harness-native Agents in Any Environment (2026)
  Xiao Yu et al.
  7.92
• Large Action Models: From Inception To Implementation (2024)
  Lu Wang, Fangkai Yang, Chaoyun Zhang, et al.
  7.86
• WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents (2025)
  Zile Qiao et al.
  7.80
• WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting (2026)
  Zhaokai Wang et al.
  7.79
• SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents (2026)
  Bingchen Zhao et al.
  7.68
• Agent Security is a Systems Problem (2026)
  Mihai Christodorescu et al.
  7.66
• Ui-venus-1.5 Technical Report (2026)
  Venus Team, Changlong Gao, Zhangxuan Gu, et al.
  7.66
• AgentSearchBench: A Benchmark for AI Agent Search in the Wild (2026)
  Bin Wu et al.
  7.60
• AIOS: LLM Agent Operating System (2024)
  Kai Mei, Xi Zhu, Wujiang Xu, et al.
  7.50
• StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents (2026)
  Ads Dawson et al.
  7.32
• GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents (2026)
  Xiao Zhou et al.
  7.25
• GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots (2026)
  Sunqi Fan et al.
  7.23
• OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents (2026)
  Chenyu Zhou et al.
  7.20
• Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion (2026)
  Stine Lyngs{\o} Beltoft et al.
  7.20