Key papers

• AgenticDataBench: A Comprehensive Benchmark for Data Agents (2026)
  Zhaoyan Sun et al.
  2.00
• WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks (2026)
  Hao Bai et al.
  1.94
• OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution (2026)
  Le Zhang et al.
  1.94
• Deep Search with Hierarchical Meta-Cognitive Monitoring Inspired by Cognitive Neuroscience (2026)
  Zhongxiang Sun et al.
  1.94
• Scaling Small Agents Through Strategy Auctions (2026)
  Lisa Alazraki et al.
  1.94
• REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents (2026)
  Zheng Chu et al.
  1.94
• ResearchGym: Evaluating Language Model Agents on Real-World AI Research (2026)
  Aniketh Garikaparthi et al.
  1.94
• SWE-rebench V2: Language-Agnostic SWE Task Collection at Scale (2026)
  Ibragim Badertdinov et al.
  1.94
• Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs? (2026)
  Jeonghye Kim et al.
  1.94
• Learning to Retrieve from Agent Trajectories (2026)
  Yuqi Zhou et al.
  1.94
• RAGEN-2: Reasoning Collapse in Agentic RL (2026)
  Zihan Wang et al.
  1.94
• OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models (2026)
  Xiaomeng Hu et al.
  1.94
• VoxMind: An End-to-End Agentic Spoken Dialogue System (2026)
  Tianle Liang et al.
  1.94
• Understanding and Enforcing Weight Disentanglement in Task Arithmetic (2026)
  Shangge Liu et al.
  1.94
• Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction (2026)
  Yuxuan Huang et al.
  1.94
• Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values (2026)
  Haonan Dong et al.
  1.94
• MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents (2026)
  Ziyun Zeng et al.
  1.94
• CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents (2026)
  Bowen Wang et al.
  1.94
• Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement (2026)
  Dingwei Chen et al.
  1.94
• Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention (2026)
  Jing Huang et al.
  1.94
• MAAT: Multi-phase Adapter-Aware Targeted Unlearning (2026)
  Suryash Yagnik et al.
  1.94
• MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft (2026)
  Tianjie Ju et al.
  1.94
• AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents (2026)
  Yiheng Shu et al.
  1.94
• Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding (2026)
  Jingyuan Huang et al.
  1.94
• Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models (2026)
  Darrien McKenzie et al.
  1.94
• HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining (2026)
  Juncheng Ma et al.
  1.94
• Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction (2026)
  Sunqi Fan et al.
  1.94
• HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents (2026)
  Qianchu Liu et al.
  1.94
• MARBLE: Multi-Aspect Reward Balance for Diffusion RL (2026)
  Canyu Zhao et al.
  1.89
• SkillOS: Learning Skill Curation for Self-Evolving Agents (2026)
  Siru Ouyang et al.
  1.89
• Signals: Trajectory Sampling and Triage for Agentic Interactions (2026)
  Shuguang Chen et al.
  1.83
• InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis (2026)
  Oliver Bentham et al.
  1.83
• Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows (2026)
  Chenxin Li et al.
  1.83
• Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions (2026)
  Mohammed Mehedi Hasan et al.
  1.72
• Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs (2026)
  Yining Hong et al.
  1.72
• User-Oriented Multi-Turn Dialogue Generation with Tool Use at scale (2026)
  Jungho Cho et al.
  1.67
• MetaChain: A Fully-Automated and Zero-Code Framework for LLM Agents (2025)
  Jiabin Tang et al.
  1.28
• APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay (2025)
  Akshara Prabhakar et al.
  1.28
• OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning (2025)
  Zhaochen Su et al.
  1.28
• Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models (2025)
  Zhiyuan Hu et al.
  1.28
• Prot2Token: A Unified Framework for Protein Modeling via Next-Token Prediction (2025)
  Mahdi Pourmirzaei et al.
  1.28
• ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models (2025)
  Mingjie Liu et al.
  1.28
• Meta-Adaptive Prompt Distillation for Few-Shot Visual Question Answering (2025)
  Akash Gupta et al.
  1.28
• Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills (2025)
  Yuquan Xie et al.
  1.28
• AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents (2025)
  Jingxu Xie et al.
  1.28
• Treasure Hunt: Real-time Targeting of the Long Tail using Training-Time Markers (2025)
  Daniel D'souza et al.
  1.28
• UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning (2025)
  Ye Liu et al.
  1.28
• RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards (2025)
  Zhilin Wang et al.
  1.28
• Visual Jigsaw Post-Training Improves MLLMs (2025)
  Penghao Wu et al.
  1.28
• Graph2Eval: Automatic Multimodal Task Generation for Agents via Knowledge Graphs (2025)
  Yurun Chen et al.
  1.28
• Search Self-play: Pushing the Frontier of Agent Capability without Supervision (2025)
  Hongliang Lu et al.
  1.28
• Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation (2025)
  Su Ho Han et al.
  1.28
• DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models (2025)
  DeepSeek-AI et al.
  1.28
• 3D-LLM: Injecting the 3D World into Large Language Models (2023)
  Yining Hong et al.
  —
• Interactive Task Planning with Language Models (2023)
  Boyi Li et al.
  —
• In-Context Learning Creates Task Vectors (2023)
  Roee Hendel et al.
  —
• JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models (2023)
  Zihao Wang et al.
  —
• COSMO: COntrastive Streamlined MultimOdal Model with Interleaved Pre-Training (2024)
  Alex Jinpeng Wang et al.
  —
• DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence (2024)
  Daya Guo et al.
  —
• ScreenAI: A Vision-Language Model for UI and Infographics Understanding (2024)
  Gilles Baechler et al.
  —