mlsanityData to 7 Oct 2026

A Survey on Large Language Model-Based Game Agents

arXiv 2404.02039 ↗First posted 2 Apr 2024cs.AIcited by 106

On the map: LLM agents and tool use → Reinforcement learning for LLM agents

Abstract (arXiv)

Game environments provide rich, controllable settings that stimulate many aspects of real-world complexity. As such, game agents offer a valuable testbed for exploring capabilities relevant to Artificial General Intelligence. Recently, the emergence of Large Language Models (LLMs) provides new opportunities to endow these agents with generalizable reasoning, memory, and adaptability in complex game environments. This survey offers an up-to-date review of LLM-based game agents (LLMGAs) through a unified reference architecture. At the single-agent level, we synthesize existing studies around three core components: memory, reasoning, and perception-action interfaces, which jointly characterize how language enables agents to perceive, think, and act. At the multi-agent level, we outline how communication protocols and organizational models support coordination, role differentiation, and large-scale social behaviors. To contextualize these designs, we introduce a challenge-centered taxonomy linking six major game genres to their dominant agent requirements, from low-latency control in action games to open-ended goal formation in sandbox worlds. A curated list of related papers is available at https://github.com/git-disl/awesome-LLM-game-agent-papers

Key facts. Cited by 106 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 192 of its 379 references that are in the map. First posted on arXiv 2 Apr 2024.

Builds on

192 of 379 references.

Closest ancestors · 23

Same direction, newest first

  1. 2024EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents18 Mar
  2. 2024Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation13 Mar
  3. 2024Language Guided Exploration for RL Agents in Text Environments5 Mar
  4. 2024Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents4 Mar
  5. 2024Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents1 Mar
  6. 2024Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization27 Feb
  7. 2024Enhance Reasoning for Large Language Models in the Game Werewolf4 Feb
  8. 2024PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models2 Feb
  9. 2024SwarmBrain: Embodied agent for real-time strategy game StarCraft II via large language models31 Jan
  10. 2024CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents19 Jan
  11. 2023Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach19 Dec
  12. 2023Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games1 Dec
11 more
  1. 2023See and Think: Embodied Agent in Virtual Environment26 Nov
  2. 2023JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models10 Nov
  3. 2023Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models31 Oct
  4. 2023Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game29 Oct
  5. 2023AvalonBench: Evaluating LLMs Playing the Game of Avalon8 Oct
  6. 2023Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-429 Sep
  7. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory25 May
  8. 2023Voyager: An Open-Ended Embodied Agent with Large Language Models25 May
  9. 2023Clembench: Using Game Play to Evaluate Chat-Optimized Language Models as Conversational Agents22 May
  10. 2023Reflexion: Language Agents with Verbal Reinforcement Learning20 Mar
  11. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge17 Jun

Other references · 169

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2023GPT-4 Technical Reportcited by 18,132
  5. 2022Training language models to follow instructions with human feedbackcited by 15,712
  6. 2017Proximal Policy Optimization Algorithmscited by 14,441
  7. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  8. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  9. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  10. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  11. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  12. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
38 more
  1. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  3. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  6. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  7. 2017Deep reinforcement learning from human preferencescited by 3,846
  8. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  9. 2023Let's Verify Step by Stepcited by 3,598
  10. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  11. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  12. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  13. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  14. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  15. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
  16. 2023A Survey of Large Language Modelscited by 2,537
  17. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  18. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  19. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  20. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  21. 2023A Survey on Evaluation of Large Language Modelscited by 1,227
  22. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  23. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  24. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,029
  25. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 895
  26. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  27. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 850
  28. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
  29. 2022A Generalist Agentcited by 802
  30. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 773
  31. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 721
  32. 2022Towards Reasoning in Large Language Models: A Surveycited by 593
  33. 2023YaRN: Efficient Context Window Extension of Large Language Modelscited by 584
  34. 2021ClipCap: CLIP Prefix for Image Captioningcited by 557
  35. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 542
  36. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  37. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 519
  38. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 478

50 most cited of 169 All 169 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 32; 2025: 52; 2026: 22.

106 papers.

Sort:

By area:

  1. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
  2. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  3. 2025Towards Scientific Intelligence: A Survey of LLM-based Scientific Agentscited by 96
  4. 2024Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attackcited by 89
  5. 2024Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Surveycited by 86
  6. 2024A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learningcited by 74
  7. 2024Agents' Room: Narrative Generation through Multi-step Collaborationcited by 57
  8. 2025Evaluating LLM-based Agents for Multi-Turn Conversations: A Surveycited by 56
  9. 2024Project Sid: Many-agent simulations toward AI civilizationcited by 46
  10. 2024LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversitycited by 42
  11. 2025OS Agents: A Survey on MLLM-based Agents for General Computing Devices Usecited by 35
  12. 2025A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrievalcited by 31
38 more
  1. 2025Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Gamescited by 30
  2. 2024BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systemscited by 26
  3. 2024Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trendscited by 26
  4. 2025Code World Models for General Game Playingcited by 25
  5. 2025Among Us: A Sandbox for Measuring and Detecting Agentic Deceptioncited by 24
  6. 2024A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarioscited by 23
  7. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  8. 2024Evaluating Large Language Models with Grid-Based Game Competitions: An Extensible LLM Benchmark and Leaderboardcited by 22
  9. 2025DSGBench: A Diverse Strategic Game Benchmark for Evaluating LLM-based Agents in Complex Decision-Making Environmentscited by 22
  10. 2024PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videoscited by 21
  11. 2024BattleAgent: Multi-modal Dynamic Emulation on Historical Battles to Complement Historical Analysiscited by 20
  12. 2025LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacracited by 20
  13. 2024Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playingcited by 17
  14. 2025Pok'eChamp: an Expert-level Minimax Language Agentcited by 16
  15. 2025Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontierscited by 14
  16. 2025Reasoning Does Not Necessarily Improve Role-Playing Abilitycited by 14
  17. 2025MEMTRACK: Evaluating Long-Term Memory and State Tracking in Multi-Platform Dynamic Agent Environmentscited by 13
  18. 2026Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Taskscited by 13
  19. 2024VideoGameBunny: Towards vision assistants for video gamescited by 11
  20. 2025Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environmentscited by 11
  21. 2026AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactionscited by 11
  22. 2024ING-VP: MLLMs cannot Play Easy Vision-based Games Yetcited by 10
  23. 2024GPT for Games: An Updated Scoping Review (2020-2024)cited by 10
  24. 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMscited by 10
  25. 2024YOLO-MARL: You Only LLM Once for Multi-Agent Reinforcement Learningcited by 9
  26. 2025SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinementcited by 9
  27. 2025Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systemscited by 9
  28. 2024LifeGPT: Topology-Agnostic Generative Pretrained Transformer Model for Cellular Automatacited by 8
  29. 2025TextGames: Learning to Self-Play Text-Based Puzzle Games via Language Model Reasoningcited by 8
  30. 2025H2R: Hierarchical Hindsight Reflection for Multi-Task LLM Agentscited by 8
  31. 2024In Context Learning and Reasoning for Symbolic Regression with Large Language Modelscited by 7
  32. 2024Who Speaks Next? Multi-party AI Discussion Leveraging the Systematics of Turn-taking in Murder Mystery Gamescited by 7
  33. 2025Among Them: A game-based framework for assessing persuasion capabilities of LLMscited by 7
  34. 2025AnimeGamer: Infinite Anime Life Simulation with Next Game State Predictioncited by 7
  35. 2025Tree-of-Reasoning: Towards Complex Medical Diagnosis via Multi-Agent Reasoning with Evidence Treecited by 7
  36. 2025Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Modelscited by 7
  37. 2025DVM: Towards Controllable LLM Agents in Social Deduction Gamescited by 6
  38. 2026Gated Differentiable Working Memory for Long-Context Language Modelingcited by 6

50 most cited of 106 All 106 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Grounding Natural Language for Multi-agent Decision-Making with Multi-agentic LLMs
  2. 2026Game-Theoretic Lens on LLM-based Multi-Agent Systems
  3. 2024Large Language Models as Agents in Two-Player Games
  4. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges
  5. 2025Playing games with Large language models: Randomness and strategy
  6. 2025Dynamic Strategy Adaptation in Multi-Agent Environments with Large Language Models
  7. 2025Game Reasoning Arena: A Framework and Benchmark for Assessing Reasoning Capabilities of Large Language Models via Game Play
  8. 2026MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs