Key papers

• R-Zero: Self-Evolving Reasoning LLM from Zero Data (2025)
  Chengsong Huang et al.
  19.72
• Agentic Reinforced Policy Optimization (2025)
  Guanting Dong et al.
  19.50
• SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning (2025)
  Haozhan Li et al.
  18.29
• Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL (2025)
  Weizhen Li et al.
  18.12
• ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU (2026)
  Fan Jiang et al.
  17.67
• Kimi K2.5: Visual Agentic Intelligence (2026)
  Kimi Team: Tongtong Bai et al.
  17.30
• AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis (2026)
  Bing Yan et al.
  16.55
• Kimi K3: Open Frontier Intelligence (2026)
  Kimi Team et al.
  16.07
• SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning (2025)
  Zhongwei Wan et al.
  16.05
• QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning (2025)
  Fanqi Wan et al.
  15.90
• EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments (2026)
  Jundong Xu et al.
  15.90
• AREX: Towards a Recursively Self-Improving Agent for Deep Research (2026)
  Shuqi Lu et al.
  15.64
• LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget (2026)
  Changhai Zhou et al.
  15.54
• Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering (2026)
  Junlin Yang et al.
  15.36
• MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent (2025)
  Hongli Yu et al.
  15.26
• Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments (2026)
  Qiuyue Wang et al.
  14.99
• Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget (2026)
  Guoxuan Chen et al.
  14.86
• Qwen-AgentWorld: Language World Models for General Agents (2026)
  Yuxin Zuo et al.
  14.85
• SkillOpt: Executive Strategy for Self-Evolving Agent Skills (2026)
  Yifan Yang et al.
  14.73
• Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning (2026)
  Chen Tang et al.
  14.53
• A New Role for Relevance: Guiding Corpus Interaction in Agentic Search (2026)
  Jiangnan Li et al.
  14.53
• APPO: Agentic Procedural Policy Optimization (2026)
  Xucong Wang et al.
  14.49
• ABot-N1: Toward a General Visual Language Navigation Foundation Model (2026)
  Ruiyan Gong et al.
  13.91
• MiniMax Sparse Attention (2026)
  Xunhao Lai et al.
  13.89
• ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory (2026)
  Jiayi Tian et al.
  13.83
• CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization (2026)
  Bo-Wen Zhang et al.
  13.72
• BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms (2026)
  Pengyu Wang et al.
  13.72
• Agent Explorative Policy Optimization for Multimodal Agentic Reasoning (2026)
  Minki Kang et al.
  13.64
• Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution (2026)
  Xucong Wang et al.
  13.56
• LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories (2026)
  Baochang Ren et al.
  13.47
• UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks (2026)
  Zhekai Chen et al.
  13.35
• UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning (2026)
  Niu Lian et al.
  13.34
• OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning (2026)
  Shuo Yang et al.
  13.31
• On-line Policy Improvement using Monte-Carlo Search (2025)
  Gerald Tesauro et al.
  13.30
• SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD (2026)
  Dongfang Li et al.
  13.27
• Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks (2026)
  Mengyu Zheng et al.
  13.22
• ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time? (2026)
  Woojung Song et al.
  13.13
• Heterogeneous Agent Collaborative Reinforcement Learning (2026)
  Zhixia Zhang et al.
  13.07
• AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents (2026)
  Xiangchen Cheng et al.
  12.98
• EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World (2026)
  Qing Zong et al.
  12.97
• ACC: Compiling Agent Trajectories for Long-Context Training (2026)
  Qisheng Su et al.
  12.95
• ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog (2026)
  Lingao Xiao et al.
  12.91
• Progress Reward Modeling for Robotic Learning: A Comprehensive Survey (2026)
  Jianshu Zhang et al.
  12.88
• FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention (2026)
  Yan Wang et al.
  12.81
• MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research (2026)
  Dingbang Wu et al.
  12.79
• BadWAM: When World-Action Models Dream Right but Act Wrong (2026)
  Qi Li et al.
  12.78
• AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report (2026)
  AlayaWorld Team et al.
  12.74
• SWE-Pruner Pro: The Coder LLM Already Knows What to Prune (2026)
  Yuhang Wang et al.
  12.73
• AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints (2026)
  Jiayu Liu et al.
  12.72
• Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent (2026)
  Lei Bai et al.
  12.68
• AWorld: Orchestrating the Training Recipe for Agentic AI (2025)
  Chengyue Yu et al.
  12.66
• EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments (2026)
  Zhilin Wang et al.
  12.56
• K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts (2026)
  Nahyun Lee et al.
  12.51
• Weak-to-Strong On-Policy Distillation (2026)
  Fangxu Yu et al.
  12.41
• The Verification Horizon: No Silver Bullet for Coding Agent Rewards (2026)
  Binghai Wang et al.
  12.31
• Planning, Creation, Usage: Benchmarking Llms For Comprehensive Tool Utilization In Real-world Complex Scenarios (2024)
  Shijue Huang, Wanjun Zhong, Jianqiao Lu, et al.
  12.31
• ResearchMath-14K: Scaling Research-Level Mathematics via Agents (2026)
  Guijin Son et al.
  12.25
• Streaming Communication in Multi-Agent Reasoning (2026)
  Zhen Yang et al.
  12.21
• AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities (2026)
  Kai Chen et al.
  12.21
• OpenCoF: Learning to Reason Through Video Generation (2026)
  Xinyan Chen et al.
  12.17