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 2403.08978cs.CLcs.LG
收藏

AutoGuide:面向大语言模型智能体的上下文感知指南自动生成与选择

AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents

University of Michigan(密歇根大学);LG AI Research(LG AI研究院)

Yao Fu, Dong-Ki Kim, Jaekyeom Kim, Sungryull Sohn, Lajanugen Logeswaran, Kyunghoon Bae, Honglak Lee

AI总结:

针对大语言模型智能体在陌生领域(如网页导航)难以通过基于演示的上下文学习有效引导的问题,本文提出AutoGuide框架,通过从离线经验自动生成遵循条件结构的简洁上下文感知指南提供相关知识,在复杂基准领域显著优于竞争基线。

摘要:

大语言模型(LLMs)的最新进展赋能了能执行各类序列决策任务的AI智能体。然而,在网页导航等智能体缺乏足够知识的陌生领域,采用基于演示的上下文学习范式有效引导LLMs表现良好被证明是困难的。本文提出一种名为AutoGuide的新型框架,通过从离线经验中自动生成上下文感知指南来解决这一局限。重要的是,每条上下文感知指南以简洁自然语言表达,遵循条件结构,清晰描述其适用的上下文。因此,我们的指南能为智能体当前决策过程提供相关知识,克服传统基于演示学习范式的局限。评估表明,AutoGuide在包括真实世界网页导航在内的复杂基准领域显著优于竞争基线。

英文摘要:

Recent advances in large language models (LLMs) have empowered AI agents capable of performing various sequential decision-making tasks. However, effectively guiding LLMs to perform well in unfamiliar domains like web navigation, where they lack sufficient knowledge, has proven to be difficult with the demonstration-based in-context learning paradigm. In this paper, we introduce a novel framework, called AutoGuide, which addresses this limitation by automatically generating context-aware guidelines from offline experiences. Importantly, each context-aware guideline is expressed in concise natural language and follows a conditional structure, clearly describing the context where it is applicable. As a result, our guidelines facilitate the provision of relevant knowledge for the agent's current decision-making process, overcoming the limitations of the conventional demonstration-based learning paradigm. Our evaluation demonstrates that AutoGuide significantly outperforms competitive baselines in complex benchmark domains, including real-world web navigation.

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。

↑