arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.31370cs.AI
收藏

HypoAgent: 一种用于知识图谱上交互式溯因假设生成的智能体框架

One Hypothesis Is Not Enough: Abductive Reasoning with Agentic Hypothesis Refinement over Knowledge Graphs

The Hong Kong University of Science and Technology(香港科学与技术大学);Beihang University(北航);Hong Kong Baptist University(香港 Baptist 大学)

Yisen Gao, Yixi Cai, Tianshi Zheng, Jiaxin Bai, Yangqiu Song

AI总结:

提出HypoAgent框架,通过三个智能体(意图识别、假设生成、根因分析)实现知识图谱上的交互式溯因假设生成,在常识和生物医学领域知识图谱上达到最优语义相似度。

摘要:

知识图谱上的溯因推理旨在生成解释观察到的实体或事实的逻辑假设。现有的可控假设生成方法允许用户通过显式条件引导这一过程,但在交互式场景中仍存在局限:它们难以在多轮对话中锚定不断变化的自然语言意图,并且在生成的假设失败时缺乏细粒度诊断。为解决这些问题,我们提出了HypoAgent,一种用于知识图谱上交互式溯因假设生成的智能体框架。HypoAgent集成了三个智能体:意图识别智能体,将用户话语和对话历史转化为可执行的知识图谱条件;假设生成智能体,根据提取的用户意图执行可控假设生成;以及根因分析智能体,诊断不可靠的假设片段并利用知识图谱邻域探测来识别支持的改进。在常识和生物医学领域特定知识图谱上的实验表明,HypoAgent在单轮、多轮和无条件设置下均达到了最先进的语义相似度。我们的代码可在https://github.com/HKUST-KnowComp/HypoAgent获取。

英文摘要:

Abductive reasoning over knowledge graphs (KGs) seeks a first-order logic hypothesis whose answer set explains a given set of observed entities. Since many hypotheses can explain the same observations, controllable hypothesis generators condition generation on entities, relations, or logical patterns, but they treat generation as a single step. A generated hypothesis may be well-formed and satisfy the given conditions yet still fail to explain the observations, and the model has no mechanism to detect or correct this mismatch. Closing the abductive cycle requires revising a discrete, structured hypothesis, which large language models cannot do reliably, even though they iterate readily in natural language. We propose HypoAgent, an agentic hypothesis refinement framework that treats condition signals not only as expressions of user intent but also as operators that steer generation. A Hypothesis Proposal Agent calls a small trained generator to propose a hypothesis. Root-cause analysis then uses fragment-level coverage to locate branches worth inspecting and gathers neighborhood evidence from the training graph. A Hypothesis Refiner Agent combines this diagnosis with previously generated hypotheses to produce updated conditions and directly revised hypotheses. HypoAgent outperforms one-shot generation in single-turn and multi-turn settings on BioKG, PharmKG8k, and DBpedia50, and in the unconditional setting on DBpedia50. Our code is available at https://github.com/HKUST-KnowComp/HypoAgent.

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。

↑