arXiv cs.CL· Qianran Ma, Muxin Liu, Grace Kim, Xiao Liang, Chris Callison-Burch·· 12 小时前AI 评分31
InsightAgents：用图蒸馏洞见为多智能体研究构思提供依据
Distill, Debate, Discover: Grounding Multi-Agent Research Ideation in Graph-Distilled Insights
AI 导读
InsightAgents 框架通过从相关论文图谱中蒸馏洞见来构建有文献依据的智能体专业知识，让智能体在辩论中共同识别研究问题并提出、质疑和细化方案。在 100 个 NLP 研究主题上，由两个 LLM 评委进行成对比较，该框架在在线和离线知识设置下五个评估维度均取得最高平均分。
正文
Abstract:Large language models (LLMs) are increasingly used to support research idea generation and scientific discovery. Multi-agent debate offers a collaborative approach to this task by bringing together diverse perspectives to develop research ideas. However, a key challenge is how to equip agents with distinct and meaningful expertise to guide their contributions. Inspired by how researchers draw on accumulated research experience during collaboration, we introduce InsightAgents, a framework that constructs literature-grounded agent expertise by distilling insights from graphs of related papers. Guided by insights that trace evolving research approaches, reveal underlying assumptions, and identify unresolved challenges, within a line of research, agents jointly identify a research problem and propose, challenge, and refine potential approaches through debate to develop a research proposal. We evaluate InsightAgents against three research idea generation frameworks on 100 NLP research topics through pairwise comparisons by two LLM judges. In both online and offline knowledge settings, InsightAgents achieves the highest average score across the five evaluation dimensions under both judges.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.33366 [cs.CL] |
| (or arXiv:2610.33366v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33366 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Qianran Ma [view email]
[v1]
Fri, 23 Oct 2026 23:27:35 UTC (393 KB)
来源：arXiv cs.CL · arxiv.org