Overview

Game-playing agents study how AI can perceive game states, plan actions, and adapt to opponents, providing testbeds for decision-making under competition, uncertainty, and long time horizons. Common approaches include tree search and Monte Carlo Tree Search, self-play reinforcement learning, regret minimization for imperfect-information games, and language- or vision-language models equipped with memory, tools, and learned world models. Evaluation spans bounded games such as chess and Go, poker and social deduction, real-time strategy, and interactive video games, using measures such as win rate, exploitability, task progress, and performance against people. Specialized systems can be highly capable in defined settings, while broad generalization remains difficult: agents still struggle with visual grounding, reliable memory, opponent modeling, and timely action in unfamiliar or long-running games.

Latest papers

CardsList

218 papers22 papers in the last four weeks, down 44% on the four weeks before. 0.2% of all new papers.

  1. Game2Player: Scaling Gameplay Experience for Visual Agents through Environment-Player Co-Development

    Nov 18, 2026Xirui Jiang, Yuxi Chen, Rui Yang +11Game-Playing AgentsAI Agent Benchmarks

  2. Stack more levels: how to get general and human-like Mario playing

    Nov 12, 2026Shinichi Arimura, Yuchen Li, Julian TogeliusGame-Playing AgentsRL for Game AI

  3. Zero-Shot Weight-Space Programming Across a Difficulty-Graded Ladder of Two-Player Games

    Nov 6, 2026Eduardo C. Garrido-MerchánWeight-Space ProgrammingWeight-Space Learning

  4. Rome Wasn't Built in One Turn: Replay-Grounded Reward Signals for Long-Horizon Freeciv Agents

    Oct 30, 2026Yanchen Liu, Xinyu Che, Brihi Joshi +6Game-Playing AgentsRL for Game AI

  5. TaskFrame: Connecting Task-Level Planning with Frame-Level Control for Game Agents

    Oct 29, 2026Guangzhi Wang, Junfu Pu, Yiran Wang +10Game-Playing AgentsLanguage Model-Based Control

  6. CoToan: Executable Rules and a Representation Contract for Reproducible Game AI Evaluation

    Oct 29, 2026Ha-Thanh NguyenAI Agent EvaluationGame-Playing Agents

  7. Inner-Learning: From Hand-Coded Beliefs to Declarative Knowledge in Trick-Taking Games

    Oct 28, 2026Stefan EdelkampKnowledge RepresentationGame-Playing Agents

  8. Gym-Anything-RT: Scaling Real-Time Environments for Vision-Language Agents

    Oct 27, 2026Pranjal Aggarwal, Sean WelleckAI Agent BenchmarksAgentic AI

  9. A Unified Arena for LLM Agents across Diverse Eurogame

    Oct 26, 2026Fengrui Zhang, Xiang Li, Ruomeng Ding +6LLM Agent EvaluationGame-Playing Agents

  10. Text Is the Bottleneck: A Small-Scale Replication of LLM Game Playing in Riichi Mahjong

    Oct 26, 2026Mingge XuGame-Playing AgentsImitation Learning

  11. Beyond What to Say: Proactive Utterance Timing with Inner Thoughts for Werewolf Agents

    Oct 23, 2026Yoshiki Tanaka, Shuya Uchiyama, Daichi Hamaguchi +1Proactive AgentsGame-Playing Agents

  12. HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games

    Oct 22, 2026Zecong Tang, Zian Guan, Yuncheng Guo +3RL for Game AIGame-Playing Agents

  13. Feedback That Backfires in Games: Do LLM Players Repeat the Move They Just Watched Fail?

    Oct 21, 2026Esmail GumaanLLM AgentsLLM Agent Reliability

  14. AgentMonopoly: Behavioral Patterns and Persona Control in LLM Agents

    Oct 21, 2026Changshun Wu, Mengyu Li, Mathis Marsault +2LLM AgentsLLM Agent Evaluation

  15. KPHarness: Co-Evolving Knowledge and Probing for Long-Horizon Gaming Harnesses

    Oct 20, 2026Zhikang Chen, Yueqing Sun, Sen Cui +6Agent Harness OptimizationLong-Horizon Agent Tasks

  16. Game of Phones: Harnessing Game Theory and LLMs in 'Bot Wars' to Counteract Phone Scams

    Oct 19, 2026Nardine Basta, Robin Carpentier, Benjamin Zi Hao Zhao +1Game-Playing AgentsLarge Language Model-Based Role-Play Simulation

  17. Teaching AI Agent to Play Poker Strategically Through Preference Optimization

    Oct 19, 2026Phurinat Polasa, Thanapon Thanadunpremdet, Phatthanasak Kraiduang +1Game-Playing AgentsPreference-Based RL

  18. ROAR: Benchmarking LMM Agents under Real-Time Constraints in Multiplayer Action-Shooter Games

    Oct 16, 2026Dawei Wang, Di Zhao, Jianran Yu +8AI Agent BenchmarksMultimodal Agents

  19. A team of Gemini 4 Argon agents beats Minecraft

    Oct 15, 2026Maxence Faldor, Satinder Singh, Roberta RaileanuGame-Playing AgentsAgentic Code Generation

  20. Player-1: Learning to Play from Synthetic Experience

    Oct 14, 2026Mingyu Ouyang, Yiran Wang, Siyuan Hu +9Game-Playing AgentsRL for Game AI