RoadMapper: 一个用于解决复杂研究问题的路线图生成的多智能体系统
RoadMapper: A Multi-Agent System for Roadmap Generation of Solving Complex Research Problems
AI总结：
本文提出RoadMapper，一个基于LLM的多智能体系统，通过分解任务生成高质量路线图，提升LLM在复杂问题解决中的性能，效率提升84%。
摘要：
人们通常利用结构化内容加速知识获取和研究问题解决。其中，路线图通过分层子任务引导研究人员逐步解决复杂问题。尽管在结构化内容生成方面取得进展，路线图生成任务仍未被探索。为填补这一空白，我们引入RoadMap，一个新基准，用于评估大语言模型（LLM）构建高质量路线图的能力。基于此，我们识别出LLM的三个局限性：（1）专业知识不足，（2）任务分解不合理，（3）逻辑关系混乱。为解决这些挑战，我们提出了RoadMapper，一个基于LLM的多智能体系统，将研究路线图生成任务分解为三个关键阶段（即初始生成、知识增强和迭代“批评-修订-评估”）。大量实验表明，RoadMapper可提高LLM在路线图生成中的能力，同时平均性能提升超过8%，节省84%的人类专家所需时间，凸显其有效性与应用潜力。
英文摘要：
People commonly leverage structured content to accelerate knowledge acquisition and research problem solving. Among these, roadmaps guide researchers through hierarchical subtasks to solve complex research problems step by step. Despite progress in structured content generation, the roadmap generation task has remained unexplored. To bridge this gap, we introduce RoadMap, a novel benchmark designed to evaluate the ability of large language models (LLMs) to construct high-quality roadmaps for solving complex research problems. Based on this, we identify three limitations of LLMs: (1) lack of professional knowledge, (2) unreasonable task decomposition, and (3) disordered logical relationships. To address these challenges, we propose RoadMapper, an LLM-based multi-agent system that decomposes the research roadmap generation task into three key stages (i.e., initial generation, knowledge augmentation, and iterative "critique-revise-evaluate"). Extensive experiments demonstrate that RoadMapper can improve LLMs' ability for roadmap generation, while enhancing average performance by more than 8% and saving 84% of the time required by human experts, highlighting its effectiveness and application potential.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
