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

TL;DR

This paper introduces a new task and dataset for proactive language agents that predict clarification needs, invoke external tools, and generate plans, using a multi-agent framework to improve real-world decision-making.

Contribution

It proposes the Ask-before-Plan benchmark and the CEP multi-agent framework to enhance LLM-based agents' proactive planning and clarification abilities.

Findings

The CEP framework outperforms baseline models in proactive planning tasks.

Trajectory tuning improves clarification accuracy.

Memory mechanisms enhance dynamic agent performance.

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.