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

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

Keywords: large language model agents, sequential decision-making

Abstract: Recent advances in large language models (LLMs) have empowered AI agents to perform 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. As a result, our guidelines facilitate the provision of relevant knowledge for the agent's current decision-making process. Our evaluation demonstrates that AutoGuide significantly outperforms competitive baselines in complex benchmark domains.

Submission Number: 32