Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

11-2024

Abstract

The evolution of large language models (LLMs) has enhanced the planning capabilities of language agents in diverse real-world scenarios. Despite these advancements, the potential of LLM-powered agents to comprehend ambiguous user instructions for reasoning and decision-making is still under exploration. In this work, we introduce a new task, Proactive Agent Planning, which requires language agents to predict clarification needs based on user-agent conversation and agent-environment interaction, invoke external tools to collect valid information, and generate a plan to fulfill the user's demands. To study this practical problem, we establish a new benchmark dataset, Ask-before-Plan. To tackle the deficiency of LLMs in proactive planning, we propose a novel multi-agent framework, Clarification-Execution-Planning (\texttt{CEP}), which consists of three agents specialized in clarification, execution, and planning. We introduce the trajectory tuning scheme for the clarification agent and static execution agent, as well as the memory recollection mechanism for the dynamic execution agent. Extensive evaluations and comprehensive analyses conducted on the Ask-before-Plan dataset validate the effectiveness of our proposed framework.

Keywords

Large language models, LLMs, Language agents, Proactive Agent Planning

Discipline

Artificial Intelligence and Robotics | Computer Sciences

Research Areas

Data Science and Engineering; Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of the Conference on Empirical Methods in Natural Language Processing 19th EMNLP 2024 : Miami, Florida, USA, November 12-16

First Page

10836

Last Page

10863

Identifier

10.48550/arXiv.2406.12639

Publisher

Association for Computational Linguistics

City or Country

USA

Additional URL

https://doi.org/10.48550/arXiv.2406.12639

Download

Share

COinS