{"list":"other","total":72,"rows":[{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195},{"id":"2606.19348","title":"DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence","created":"2026-04-26","cited_by_count":1040},{"id":"2507.18071","title":"Group Sequence Policy Optimization","created":"2025-07-24","cited_by_count":835},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"id":"2602.15763","title":"GLM-5: from Vibe Coding to Agentic Engineering","created":"2026-02-17","cited_by_count":587},{"id":"2601.11868","title":"Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces","created":"2026-01-17","cited_by_count":585},{"id":"2602.02276","title":"Kimi K2.5: Visual Agentic Intelligence","created":"2026-02-02","cited_by_count":501},{"id":"2602.15922","title":"World Action Models are Zero-shot Policies","created":"2026-02-17","cited_by_count":465},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"2504.20073","title":"RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning","created":"2025-04-24","cited_by_count":386},{"id":"2507.17746","title":"Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains","created":"2025-07-23","cited_by_count":366},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328},{"id":"2408.14837","title":"Diffusion Models Are Real-Time Game Engines","created":"2024-08-27","cited_by_count":296},{"id":"2509.16941","title":"SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?","created":"2025-09-21","cited_by_count":279},{"id":"2505.04588","title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","created":"2025-05-07","cited_by_count":208},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200},{"id":"2510.04374","title":"GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks","created":"2025-10-05","cited_by_count":158},{"id":"2509.24527","title":"Training Agents Inside of Scalable World Models","created":"2025-09-29","cited_by_count":136},{"id":"2510.08558","title":"Agent Learning via Early Experience","created":"2025-10-09","cited_by_count":85},{"id":"2510.25726","title":"The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution","created":"2025-10-29","cited_by_count":85},{"id":"2505.14357","title":"Vid2World: Crafting Video Diffusion Models to Interactive World Models","created":"2025-05-20","cited_by_count":76},{"id":"2508.07999","title":"WideSearch: Benchmarking Agentic Broad Info-Seeking","created":"2025-08-11","cited_by_count":69},{"id":"2601.05808","title":"EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis","created":"2026-01-09","cited_by_count":63},{"id":"2602.05125","title":"Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks","created":"2026-02-04","cited_by_count":62},{"id":"2511.01824","title":"Simulating Environments with Reasoning Models for Agent Training","created":"2025-11-03","cited_by_count":57},{"id":"2509.13311","title":"Towards General Agentic Intelligence via Environment Scaling","created":"2025-09-16","cited_by_count":54},{"id":"2601.16443","title":"Endless Terminals: Scaling RL Environments for Terminal Agents","created":"2026-01-23","cited_by_count":54},{"id":"2604.18292","title":"Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence","created":"2026-04-20","cited_by_count":54},{"id":"2601.15876","title":"EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience","created":"2026-01-22","cited_by_count":53},{"id":"2406.06485","title":"Can Language Models Serve as Text-Based World Simulators?","created":"2024-06-10","cited_by_count":52},{"id":"2605.00080","title":"World Model for Robot Learning: A Comprehensive Survey","created":"2026-04-30","cited_by_count":46},{"id":"2512.19682","title":"GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators","created":"2025-12-22","cited_by_count":42},{"id":"2505.13934","title":"RLVR-World: Training World Models with Reinforcement Learning","created":"2025-05-20","cited_by_count":40},{"id":"2509.13310","title":"Scaling Agents via Continual Pre-training","created":"2025-09-16","cited_by_count":40},{"id":"2509.24002","title":"MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use","created":"2025-09-28","cited_by_count":39},{"id":"2604.13602","title":"Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges","created":"2026-04-15","cited_by_count":33},{"id":"2602.06820","title":"ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent Training","created":"2026-02-06","cited_by_count":32},{"id":"2602.07274","title":"TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents","created":"2026-02-06","cited_by_count":29},{"id":"2602.09856","title":"Code2World: A GUI World Model via Renderable Code Generation","created":"2026-02-10","cited_by_count":29},{"id":"2601.04126","title":"InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training","created":"2026-01-07","cited_by_count":27},{"id":"2602.03419","title":"SWE-World: Building Software Engineering Agents in Docker-Free Environments","created":"2026-02-03","cited_by_count":25},{"id":"2602.02488","title":"RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System","created":"2026-02-02","cited_by_count":24},{"id":"2601.04035","title":"MobileDreamer: Generative Sketch World Model for GUI Agent","created":"2026-01-07","cited_by_count":23},{"id":"2602.09892","title":"Immersion in the GitHub Universe: Scaling Coding Agents to Mastery","created":"2026-02-10","cited_by_count":22},{"id":"2602.14296","title":"AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines","created":"2026-02-15","cited_by_count":21},{"id":"2601.02439","title":"WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks","created":"2026-01-05","cited_by_count":19},{"id":"2602.02361","title":"SWE-Universe: Scale Real-World Verifiable Environments to Millions","created":"2026-02-02","cited_by_count":19},{"id":"2510.14969","title":"LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training","created":"2025-10-16","cited_by_count":18},{"id":"2602.14093","title":"GUI-GENESIS: Automated Synthesis of Efficient Environments with Verifiable Rewards for GUI Agent Post-Training","created":"2026-02-15","cited_by_count":18},{"id":"2512.22857","title":"AutoForge: Automated Environment Synthesis for Agentic Reinforcement Learning","created":"2025-12-28","cited_by_count":17},{"id":"2602.17365","title":"Computer-Using World Model","created":"2026-02-19","cited_by_count":16},{"id":"2508.10874","title":"SSRL: Self-Search Reinforcement Learning","created":"2025-08-14","cited_by_count":14},{"id":"2603.13023","title":"daVinci-Env: Open SWE Environment Synthesis at Scale","created":"2026-03-13","cited_by_count":14},{"id":"2511.09586","title":"Environment Scaling for Interactive Agentic Experience Collection: A Survey","created":"2025-11-12","cited_by_count":13},{"id":"2602.01576","title":"Generative Visual Code Mobile World Models","created":"2026-02-02","cited_by_count":13},{"id":"2603.10505","title":"Safe and Scalable Web Agent Learning via Recreated Websites","created":"2026-03-11","cited_by_count":11},{"id":"2604.04872","title":"Synthetic Sandbox for Training Machine Learning Engineering Agents","created":"2026-04-06","cited_by_count":11},{"id":"2604.17931","title":"LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent","created":"2026-04-20","cited_by_count":10},{"id":"2601.04809","title":"SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning","created":"2026-01-08","cited_by_count":8},{"id":"2601.21558","title":"ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas","created":"2026-01-29","cited_by_count":8},{"id":"2604.18543","title":"ClawEnvKit: Automatic Environment Generation for Claw-Like Agents","created":"2026-04-20","cited_by_count":8},{"id":"2509.25779","title":"Planner-R1: Reward Shaping Enables Efficient Agentic RL with Smaller LLMs","created":"2025-09-30","cited_by_count":7},{"id":"2510.22732","title":"WebATLAS: An LLM Agent with Experience-Driven Memory and Action Simulation","created":"2025-10-26","cited_by_count":6},{"id":"2603.05044","title":"WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents","created":"2026-03-05","cited_by_count":6},{"id":"2604.09813","title":"Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning","created":"2026-04-10","cited_by_count":6},{"id":"2509.21733","title":"UISim: An Interactive Image-Based UI Simulator for Dynamic Mobile Environments","created":"2025-09-26","cited_by_count":5},{"id":"2602.06130","title":"Self-Improving World Modelling with Latent Actions","created":"2026-02-05","cited_by_count":5},{"id":"2605.06761","title":"Weblica: Scalable and Reproducible Training Environments for Visual Web Agents","created":"2026-05-07","cited_by_count":4},{"id":"2604.09815","title":"EE-MCP: Self-Evolving MCP-GUI Agents via Automated Environment Generation and Experience Learning","created":"2026-04-10","cited_by_count":3},{"id":"2604.17739","title":"Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model","created":"2026-04-20","cited_by_count":1}],"next_cursor":null}