# OntoAct：通过本体抽象实现基于假设的神经符号智能体

> 原文链接：https://robotics.hellobike.com/papers/2026-10-15-2610-21983
> 频道：papers | 更新日期：2026-10-15 | 标签：arxiv, cs.RO
> 核心摘要：OntoAct将经验抽象为本体公理，结合LLM假设生成与符号验证，在Tacit-FLE、Mars和ALFWorld验证。

# OntoAct：通过本体抽象实现基于假设的神经符号智能体

::: v-pre
> 原文链接：[OntoAct: Hypothesis-Based Neuro-Symbolic Agents through Ontological Abstraction](https://arxiv.org/abs/2610.21983)（arXiv 2610.21983 · 发布日期：2026-10-15）

**OntoAct: Hypothesis-Based Neuro-Symbolic Agents through Ontological Abstraction**

OntoAct将经验抽象为本体公理，结合LLM假设生成与符号验证，在Tacit-FLE、Mars和ALFWorld验证。

## 核心要点

- 从经验学习需恢复可复用知识，并判断其何时适用于新情境。
- 将个体经验转为实体类型、关系和条件上的公理，供LLM提出假设与动作。
- 符号验证器依据当前观测评估支持条件，发现缺失证据并随交互更新评估。
- 在Tacit-FLE、Mars和ALFWorld上，取得领先任务表现且交互和推理高效。

**验证范围与局限**：验证范围包括Tacit-FLE、Mars和ALFWorld；Tacit-FLE面向现有工厂隐藏故障诊断与修复。

## 英文摘要 (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.

作者：Donghyeok Lee, Bong Gyun Kang, Junyong Ahn, Sungroh Yoon
:::

## 原始参考来源 (Sources)

- [arXiv 2610.21983：OntoAct: Hypothesis-Based Neuro-Symbolic Agents through Ontological Abstraction](https://arxiv.org/abs/2610.21983)