arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2312.15224cs.AIcs.HC
收藏

基于LLM的层次化语言智能体用于实时人机协作

LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination

Tsinghua University(清华大学)

Jijia Liu, Chao Yu, Jiaxuan Gao, Yuqing Xie, Qingmin Liao, Yi Wu, Yu Wang

AI总结:

提出层次化语言智能体HLA,通过慢思考、快思考和执行器三模块结合,在Overcooked游戏中实现强推理与实时执行,显著提升人机协作效果。

摘要:

由大型语言模型(LLMs)驱动的AI智能体取得了重大进展,使其能够协助人类完成各种复杂任务,并引领了人机协作的革命。基于LLM的智能体通常需要调用LLM API并采用人工设计的复杂提示,这导致了高推理延迟。尽管这种范式在交互需求极少的场景(如代码生成)中表现良好,但它不适用于高度交互和实时的应用,如游戏。传统游戏AI通常采用小模型或反应式策略,能够实现快速推理,但任务完成和交互能力有限。在本研究中,我们以《Overcooked》作为测试平台,玩家可以使用自然语言进行交流并合作完成订单。我们提出了一种用于人机协作的层次化语言智能体(HLA),它既能提供强大的推理能力,又能保持实时执行。具体而言,HLA采用层次化框架,包含三个模块:一个熟练的LLM,称为“慢思考”,用于意图推理和语言交互;一个轻量级LLM,称为“快思考”,用于生成宏观动作;以及一个反应式策略,称为“执行器”,用于将宏观动作转化为原子动作。人类研究表明,HLA在协作能力、响应速度和语言交流一致性方面优于其他基线智能体,包括仅使用慢思考的智能体和仅使用快思考的智能体。

英文摘要:

AI agents powered by Large Language Models (LLMs) have made significant advances, enabling them to assist humans in diverse complex tasks and leading to a revolution in human-AI coordination. LLM-powered agents typically require invoking LLM APIs and employing artificially designed complex prompts, which results in high inference latency. While this paradigm works well in scenarios with minimal interactive demands, such as code generation, it is unsuitable for highly interactive and real-time applications, such as gaming. Traditional gaming AI often employs small models or reactive policies, enabling fast inference but offering limited task completion and interaction abilities. In this work, we consider Overcooked as our testbed where players could communicate with natural language and cooperate to serve orders. We propose a Hierarchical Language Agent (HLA) for human-AI coordination that provides both strong reasoning abilities while keeping real-time execution. In particular, HLA adopts a hierarchical framework and comprises three modules: a proficient LLM, referred to as Slow Mind, for intention reasoning and language interaction, a lightweight LLM, referred to as Fast Mind, for generating macro actions, and a reactive policy, referred to as Executor, for transforming macro actions into atomic actions. Human studies show that HLA outperforms other baseline agents, including slow-mind-only agents and fast-mind-only agents, with stronger cooperation abilities, faster responses, and more consistent language communications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑