基于大语言模型的游戏智能体综述

Stars Forks

🔥 基于 LLM 的游戏智能体必读论文列表。

💫 我们将每周持续更新此 GitHub 列表。（上次更新时间：2026/02/13）

📝 如果您发现了尚未收录的相关论文，欢迎提交 Issue 或 Pull Request。

📘 我们的综述论文是一份动态更新的文档，第三版计划于一个月内发布。

论文更新历史：

第一版：2024 年 4 月 2 日
第二版：2025 年 3 月 30 日
第三版：2025 年 10 月 27 日

[2019/09] Interactive Fiction Games: A Colossal Adventure AAAI 2020 [paper] [code]
[2020/10] ALFWorld: Aligning Text and Embodied Environments for Interactive Learning ICLR 2021 [paper][code]
[2022/03] ScienceWorld: Is your Agent Smarter than a 5th Grader? EMNLP 2022 [paper] [code]
[2022/10] ReAct: Synergizing Reasoning and Acting in Language Models ICLR 2023 [paper] [code]
[2023/03] Reflexion: Language Agents with Verbal Reinforcement Learning NeurIPS 2023 [paper] [code]
[2023/04] Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions arXiv [paper]
[2023/05] SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks NeurIPS 2023 [paper] [code]
[2023/10] FireAct: Toward Language Agent Fine-tuning arXiv [paper][code]
[2023/10] Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models ICML 2024 [paper][code]
[2023/11] ADaPT: As-Needed Decomposition and Planning with Language Models arXiv [paper][code]
[2024/02] Soft Self-Consistency Improves Language Model Agents arXiv [paper][code]
[2024/02] Empowering Large Language Model Agents through Action Learning arXiv [paper][code]
[2024/03] KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents arXiv [paper][code]
[2024/03] Language Guided Exploration for RL Agents in Text Environments arXiv [paper][code]
[2024/03] Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents ACL 2024 [paper][code]
[2024/04] **Learnin

git-disl/awesome-LLM-game-agent-papers

基于大语言模型的游戏智能体综述

目录

冒险类游戏

文字冒险游戏