发表机构
Vanderbilt University; Air Force Research Laboratory（范德堡大学; 空军研究实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
AutoKD是一个多智能体框架，通过持久洞察图实现累积性自主知识发现，在三个数据集上覆盖已知发现并产生补充人类研究的实质性发现。
AI 中文摘要
在数据丰富的领域中，科学发现目前受到人类带宽的限制：真实世界数据的数量和复杂性的增长远远超过研究人员阅读、推理和综合的速度。最近基于LLM的多智能体系统已开始自动化研究周期的部分环节，但它们针对的是验证本身无法自动化的场景中的假设生成，且每次运行都是一次性的，没有机制让发现积累或引导后续探究。本文介绍了AutoKD，一个用于自主知识发现的多智能体框架，它既是计算性的又是累积性的，允许经过验证的发现持续存在并指导后续探究。六个协调的LLM智能体在一个开放式的发现循环中协作，其中被接受的发现存储在一个持久的洞察图中，该图既作为长期记忆又作为探索引导机制。我们从两个角度在三个不同的数据集上评估AutoKD：针对已发表发现的开放式质量，以及通过文献衍生查询的条件式质量。在这两个评估角度中，AutoKD覆盖了已知发现并浮现出补充人类驱动研究的实质性发现。我们的代码可在以下网址获取：此https URL。
英文摘要
Scientific discovery in data-rich domains is currently constrained by human bandwidth: the growth in the volume and complexity of real-world data far outpaces the rate at which researchers can read, reason, and synthesize. Recent LLM-based multi-agent systems have begun to automate portions of the research cycle, but they target hypothesis generation in settings where validation cannot itself be automated, and each run is one-shot, with no mechanism for findings to accumulate or steer subsequent inquiry. This paper introduces AutoKD, a multi-agent framework for autonomous knowledge discovery that is both computational and cumulative, allowing validated findings to persist and inform subsequent inquiry. Six coordinated LLM agents collaborate in an open-ended discovery loop, where accepted findings are stored in a persistent insight graph that serves as both long-term memory and an exploration-steering mechanism. We evaluate AutoKD on three diverse datasets from two perspectives: Open-ended Quality against published findings, and Conditioned Quality via literature-derived queries. Across both evaluation perspectives, AutoKD covers known findings and surfaces substantive discoveries that complement human-driven research. Our code is available at https://github.com/GeQinwen/AutoKD.
