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

arXiv:2403.08978v1 Announce Type: cross
Abstract: The primary limitation of large language models (LLMs) is their restricted understanding of the world. This poses significant difficulties for LLM-based agents, particularly in domains where pre-trained LLMs lack sufficient knowledge. In this paper, we introduce a novel framework, called AutoGuide, that bridges the knowledge gap in pre-trained LLMs by leveraging implicit knowledge in offline experiences. Specifically, AutoGuide effectively extracts knowledge embedded in offline data by extracting a set of state-aware guidelines. Importantly, each state-aware …

abstract agents arxiv automated cs.cl cs.lg domains framework guidelines knowledge language language model language models large language large language model large language models llm llms novel paper state type understanding world