Ask-before-Plan: Proactive Language Agents for Real-World Planning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xuan, Deng, Yang, Ren, Zifeng, Ng, See-Kiong, Chua, Tat-Seng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917792982237184
author Zhang, Xuan
Deng, Yang
Ren, Zifeng
Ng, See-Kiong
Chua, Tat-Seng
author_facet Zhang, Xuan
Deng, Yang
Ren, Zifeng
Ng, See-Kiong
Chua, Tat-Seng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_12639
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Ask-before-Plan: Proactive Language Agents for Real-World Planning
Zhang, Xuan
Deng, Yang
Ren, Zifeng
Ng, See-Kiong
Chua, Tat-Seng
Computation and Language
Artificial Intelligence
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.
title Ask-before-Plan: Proactive Language Agents for Real-World Planning
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2406.12639