arXiv cs.AI· Donghyeok Lee, Bong Gyun Kang, Junyong Ahn, Sungroh Yoon·· 2 天前AI 评分32
OntoAct：基于本体抽象与假设的神经符号智能体框架
OntoAct: Hypothesis-Based Neuro-Symbolic Agents through Ontological Abstraction
AI 导读
OntoAct 是一个基于本体抽象的假设驱动神经符号框架，将个体经验转化为实体类型、关系与条件上的公理，由 LLM 提出假设与动作、符号验证器依据当前观测核验其成立条件。
正文 · 原文
Abstract:Learning from experience requires recovering reusable knowledge and determining when it applies to a new situation. We introduce OntoAct, a hypothesis-based neuro-symbolic framework built on ontological abstraction. OntoAct turns individual experiences into axioms over entity types, relations, and conditions, making their underlying patterns reusable across situations. A large language model (LLM) uses this world knowledge to propose hypotheses and actions, while a symbolic verifier assesses their supporting conditions against current observations. Verification identifies missing evidence, and new observations and intervention outcomes update hypothesis assessments and guide subsequent actions. We also introduce Tacit-FLE, a benchmark built on the Factorio Learning Environment (FLE) for diagnosing and repairing hidden faults in existing factories using inherited operational records. Its synthetic maintenance corpus distributes evidence across records, and an executed repair may leave the fault unresolved, requiring agents to reassess their diagnoses through interaction. Across Tacit-FLE, Mars, and ALFWorld, OntoAct achieves leading task performance with efficient interaction and inference.
| Comments: | 49 pages, 13 figures, 33 tables. Preprint, under review |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.21983 [cs.AI] |
| (or arXiv:2610.21983v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21983 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Donghyeok Lee [view email]
[v1]
Thu, 15 Oct 2026 14:34:15 UTC (2,411 KB)
来源：arXiv cs.AI · arxiv.org