{"total":55,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2603.22435","title":"CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation","created":"2026-03-23","cited_by_count":88,"area":"vla"},{"id":"2510.16907","title":"VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents","created":"2025-10-19","cited_by_count":62,"area":"wm"},{"id":"2602.22769","title":"AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications","created":"2026-02-26","cited_by_count":53,"area":"agents"},{"id":"2505.18134","title":"VideoGameBench: Can Vision-Language Models complete popular video games?","created":"2025-05-23","cited_by_count":36,"area":"mllm"},{"id":"2506.03610","title":"Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games","created":"2025-06-04","cited_by_count":31,"area":"agents"},{"id":"2510.11062","title":"Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs","created":"2025-10-13","cited_by_count":28,"area":"lr"},{"id":"2510.04542","title":"Code World Models for General Game Playing","created":"2025-10-06","cited_by_count":26,"area":"wm"},{"id":"2605.13527","title":"MMSkills: Towards Multimodal Skills for General Visual Agents","created":"2026-05-13","cited_by_count":16,"area":null},{"id":"2604.20987","title":"Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks","created":"2026-04-22","cited_by_count":15,"area":"agents"},{"id":"2509.25052","title":"Cogito, Ergo Ludo: An Agent that Learns to Play by Reasoning and Planning","created":"2025-09-29","cited_by_count":12,"area":"lr"},{"id":"2605.17637","title":"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games","created":"2026-05-17","cited_by_count":12,"area":"agents"},{"id":"2507.11633","title":"General Modular Harness for LLM Agents in Multi-Turn Gaming Environments","created":"2025-07-15","cited_by_count":11,"area":"agents"},{"id":"2508.03368","title":"Game Reasoning Arena: A Framework and Benchmark for Assessing Reasoning Capabilities of Large Language Models via Game Play","created":"2025-08-05","cited_by_count":11,"area":"lr"},{"id":"2601.16973","title":"VisGym: Diverse, Customizable, Scalable Environments for Multimodal Agents","created":"2026-01-23","cited_by_count":11,"area":"mllm"},{"id":"2508.08501","title":"GVGAI-LLM: Evaluating Large Language Model Agents with Infinite Games","created":"2025-08-11","cited_by_count":9,"area":"agents"},{"id":"2603.06656","title":"GameVerse: Can Vision-Language Models Learn from Video-based Reflection?","created":"2026-03-01","cited_by_count":8,"area":"mllm"},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2603.09022","title":"MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games","created":"2026-03-09","cited_by_count":5,"area":"agents"},{"id":"2605.29512","title":"MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs","created":"2026-05-28","cited_by_count":5,"area":"lr"},{"id":"2605.30931","title":"MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft","created":"2026-05-29","cited_by_count":4,"area":"agents"},{"id":"2606.09826","title":"OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics","created":"2026-06-08","cited_by_count":4,"area":"agents"},{"id":"2509.01052","title":"FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Games","created":"2025-09-01","cited_by_count":3,"area":"agents"},{"id":"2603.15432","title":"Gym-V: A Unified Vision Environment System for Agentic Vision Research","created":"2026-03-16","cited_by_count":3,"area":"agents"},{"id":"2605.00347","title":"Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning","created":"2026-05-01","cited_by_count":3,"area":"mllm"},{"id":"2605.09965","title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2605.14537","title":"Cattle Trade: A Multi-Agent Benchmark for LLM Bluffing, Bidding, and Bargaining","created":"2026-05-14","cited_by_count":3,"area":"lr"},{"id":"2606.24893","title":"AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2607.25308","title":"CAST: Game Solvers as Turn-Level Teachers for LLM Agents","created":"2026-07-28","cited_by_count":3,"area":"agents"},{"id":"2601.20856","title":"SokoBench: Evaluating Long-Horizon Planning and Reasoning in Large Language Models","created":"2026-01-28","cited_by_count":2,"area":"lr"},{"id":"2602.21262","title":"Under the Influence: Quantifying Persuasion and Vigilance in Large Language Models","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2603.18480","title":"Do Vision Language Models Understand Human Engagement in Games?","created":"2026-03-19","cited_by_count":1,"area":"mllm"},{"id":"2604.20043","title":"TriEx: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLMs","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2608.27456","title":"UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City","created":"2026-08-27","cited_by_count":1,"area":"mllm"},{"id":"2509.17978","title":"The STAR-XAI Protocol: A Framework for Inducing and Verifying Agency, Reasoning, and Reliability in AI Agents","created":"2025-09-22","cited_by_count":0,"area":"lr"},{"id":"2512.19210","title":"Observer, Not Player: Simulating Theory of Mind in LLMs through Game Observation","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2602.19160","title":"Reasoning Capabilities of Large Language Models. Lessons Learned from General Game Playing","created":"2026-02-22","cited_by_count":0,"area":"lr"},{"id":"2603.01260","title":"MOSAIC: A Universal Agent-Level Interface for Cross-Paradigm Agent Mixing and Human-AI Collaboration","created":"2026-03-01","cited_by_count":0,"area":"agents"},{"id":"2603.02348","title":"Same Pieces, Different Servers: A Tetris Benchmark for AI Agents as Served","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2604.09594","title":"Spatial Competence Benchmark","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.17696","title":"Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-Play","created":"2026-04-20","cited_by_count":0,"area":"lr"},{"id":"2605.29653","title":"PTCG-Bench: Can LLM Agents Master Pok\\'emon Trading Card Game?","created":"2026-05-28","cited_by_count":0,"area":"agents"},{"id":"2606.19338","title":"Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games","created":"2026-06-17","cited_by_count":0,"area":"mllm"},{"id":"2608.07490","title":"Experience-Sensitive Game Learning: A Behavioral Study of Humans and Language Agents","created":"2026-06-15","cited_by_count":0,"area":"agents"},{"id":"2608.23969","title":"Investigating Knowledge Transfer Across Interactive Dialogue Games","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.15683","title":"V-ICAL Bench: Evaluating Video In-Context Learning for Multimodal Agents in Interactive Environments","created":"2026-09-14","cited_by_count":0,"area":"agents"},{"id":"2609.18996","title":"Compiled Agency: Frontier General-Purpose Coding Agents Build Winning Game Players from Bare Interaction - from Flappy Bird to StarCraft II and Civilization","created":"2026-07-17","cited_by_count":0,"area":"agents"},{"id":"2609.22308","title":"GameReplica: A Benchmark for Black-Box Visual Game Replication by Vision-Language Agents","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.30936","title":"Self-Play Search Distillation for Large Language Model Reasoning","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.32208","title":"Witness: Discovery, Deciphering, and Epiphany in Interactive Puzzle Environments","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.34214","title":"GlyphBench: A Playground for Language-Model Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.34769","title":"LongPuzzleBench: Evaluating GUI Agents on Long-Horizon Visual Puzzles","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.38891","title":"Consistent Plan-Act for Long-Horizon Agentic Tasks","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.12341","title":"Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition","created":"2026-10-08","cited_by_count":0,"area":"deeprl"},{"id":"2610.18834","title":"Game2Real-Bench: Do Toy Games Reveal and Transfer to Real-World Visual Reasoning?","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}