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

2024/03/13 by Yao Fu, Dong Ki Kim, Fu, Yao +11 · 17 citations
Business, Management and Accounting · Computer Science · #Business Process Modeling and Analysis #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Model-Driven Software Engineering Techniques #Multi-Agent Systems and Negotiation

paper · pdf · doi:10.48550/arxiv.2403.08978

openalex publication_date 2024/03/13 · openalex created_date 2024/03/16 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• In-Context Distillation with Self-Consistency Cascades: A Simple, Training-Free Way to Reduce LLM Agent Costs
• OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability
• Experiential Reflective Learning for Self-Improving LLM Agents
• SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution
• JEF-Hinter: Leveraging Offline Knowledge for Improving Web Agents Adaptation
• Fine-tuning with RAG for Improving LLM Learning of New Skills
• ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
• Beyond Manuals and Tasks: Instance-Level Context Learning for LLM Agents
• D-Artemis: A Deliberative Cognitive Framework for Mobile GUI Multi-Agents
• Prompt-aware classifier free guidance for diffusion models
• From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users
• StageACT: Stage-Conditioned Imitation for Robust Humanoid Door Opening
• H²R: Hierarchical Hindsight Reflection for Multi-Task LLM Agents
• PG-Agent: An Agent Powered by Page Graph
• SWE-Exp: Experience-Driven Software Issue Resolution
• Evaluation and Benchmarking of LLM Agents: A Survey
• Enter the Mind Palace: Reasoning and Planning for Long-term Active Embodied Question Answering

Related

• GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents
• AutoPlan: Automatic Planning of Interactive Decision-Making Tasks With Large Language Models
• Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents
• AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning
• Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks