cs.AI updates on arXiv.org 16小时前
General Modular Harness for LLM Agents in Multi-Turn Gaming Environments
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出一种模块化游戏AI套件设计,通过感知、记忆和推理组件,使LLM或VLM模型在多种游戏环境中表现优异,无需特定领域工程。实验表明,该套件能显著提升游戏性能,并揭示不同模块在不同场景下的贡献模式。

arXiv:2507.11633v1 Announce Type: new Abstract: 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.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

LLM 游戏AI 模块化设计
相关文章