用模块化框架让大模型玩转各类游戏，无需针对每款游戏重写代码。
General Modular Harness for LLM Agents in Multi-Turn Gaming Environments
- 分感知、记忆、推理三模块，统一驱动大模型玩多种游戏。
- 在长时谜题中记忆模块最重要，在视觉混乱游戏中感知更关键。
- 适合研究通用智能体或想快速测试模型能力的研究者。
我们提出一种模块化框架，包含感知、记忆和推理组件，使单一LLM或视觉语言模型（VLM）能够无需领域特定工程即可应对多种多轮游戏环境。通过经典与现代游戏套件作为低门槛、高多样性的测试平台，该框架提供统一流程，分析各模块在动态交互场景中的性能影响。大量实验表明，相比未使用该框架的基线，本框架显著提升游戏表现，并揭示不同模块的贡献差异：在长时程谜题中记忆占主导，而在视觉噪声较大的街机类游戏中感知至关重要。这些发现凸显了该模块化设计在推动通用智能体发展上的有效性，尤其基于游戏在人类日常经验中的普遍性。
原文摘要 · Abstract (English)
We introduce a modular harness design for LLM agents that composes of perception, memory, and reasoning components, enabling a single LLM or VLM backbone to tackle a wide spectrum of multi turn gaming environments without domain-specific engineering. Using classic and modern game suites as low-barrier, high-diversity testbeds, our framework provides a unified workflow for analyzing how each module affects performance across dynamic interactive settings. Extensive experiments demonstrate that the harness lifts gameplay performance consistently over un-harnessed baselines and reveals distinct contribution patterns, for example, memory dominates in long-horizon puzzles while perception is critical in vision noisy arcades. These findings highlight the effectiveness of our modular harness design in advancing general-purpose agent, given the familiarity and ubiquity of games in everyday human experience.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。