awesome-LLM-game-agent-papers
git-disl/awesome-LLM-game-agent-papers
A comprehensive survey and curated repository of academic research papers focused on Large Language Model-based game agents. It classifies literature by genre and mechanism to support research in AI gameplay and multi-agent systems.
948 33No licenseUpdated 2026-06-07
56
FairOverview
This repository provides an extensive, categorized collection of academic papers exploring how large language models and vision-language models can be applied to game agents. It organizes research across various genres like Minecraft, text adventures, and simulations, as well as core mechanisms such as planning, memory, and multi-agent coordination, serving as a vital resource for AI researchers and engineers.
Capabilities
- ▸Categorized paper index by genre and mechanism
- ▸Curated links to arXiv preprints and open-source implementations
- ▸Weekly updates tracking new research literature
Best for
Discovering state-of-the-art research papers on LLM-based game agents, Exploring methodologies for multi-agent cooperation and competition in virtual environments, Investigating planning, memory, and world-model architectures for embodied AI, Finding benchmarks and evaluation datasets for interactive game agents
Works with
Claude CodeChatGPTCursorGitHub Copilot
Evoa Score breakdown= Σ (score × weight)
56Task usefulness20%65 → +13.0
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%50 → +7.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%85 → +12.8
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%40 → +4.8
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%100 → +15.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%20 → +2.0
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%75 → +6.0
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%100 → +5.0
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total66.0 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
The content consists entirely of public academic paper links and bibliographic metadata, presenting no security risks.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.