用多智能体系统生成研究问题的分步路线图，提升效率与质量。
RoadMapper: A Multi-Agent System for Roadmap Generation of Solving Complex Research Problems
- 设计多智能体流程：生成-增强-迭代修正
- 相比人类专家提速84%，平均性能提升超8%
- 适合需要系统化研究规划的科研人员
人们通常借助结构化内容加速知识获取与研究问题求解。其中，路线图通过分层子任务引导研究人员逐步解决复杂研究问题。尽管结构化内容生成已取得进展，路线图生成任务仍鲜有探索。为此，我们提出RoadMap，一个用于评估大语言模型（LLMs）生成高质量研究路线图能力的新基准。基于此，我们识别出三类局限：（1）专业知识不足，（2）任务分解不合理，（3）逻辑关系混乱。为应对挑战，我们提出RoadMapper，一种基于LLM的多智能体系统，将路线图生成分为三个关键阶段：初始生成、知识增强、以及迭代“批判-修订-评估”。大量实验表明，RoadMapper能显著提升LLMs的路线图生成能力，平均性能提升超过8%，同时节省84%的人工专家耗时，展现出其有效性和应用潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。