基于动态本体的有效可靠大语言模型智能体研究
Toward Effective and Reliable LLM Agents via Dynamic Ontology
浏览论文内容
中文总结 AI 辅助
本文提出OaK框架，通过动态构建优化面向任务的本体论，在TravelPlanner等数据集上验证其可提升LLM智能体的证据基础与多步推理可靠性。
中文摘要 AI 辅助
大语言模型（LLM）智能体严重依赖模型参数中编码的知识或以非结构化上下文形式呈现的知识，在特定领域任务中，这会使重要的语义关联隐含，常导致证据使用不完整和多步决策脆弱。本体论为将领域概念和关系外部化为机器可解释结构提供了途径，但传统构建任务可用本体论需要领域专家付出大量努力且难以扩展，自动构建也颇具挑战：看似语义合理的本体论可能不包含实际决策所需的关系结构。本文提出OaK（本体即内核）框架，该框架为LLM智能体动态构建和优化面向任务的本体论。给定任务需求和训练数据，OaK构建本体论及其知识图谱，生成用于图推理的任务适配函数，并利用评判者反馈迭代优化两者。通过明确相关概念和关系，本体论为知识检索和多步决策提供基础。我们在TravelPlanner、CRMArenaPro和ToolQA上对OaK进行评估，结果显示OaK改进了标准LLM智能体，增强了证据基础，并提高了多步推理的可靠性。
英文摘要
Large language model (LLM) agents rely heavily on knowledge encoded in model parameters or presented as unstructured context. In domain-specific tasks, this leaves important semantic connections implicit. This often results in incomplete evidence use and brittle multi-step decisions. Ontologies offer a way to externalize domain concepts and relations as machine-interpretable structures, but constructing task-usable ontologies traditionally requires substantial effort from domain experts and is difficult to scale. Automatic construction is also challenging: an ontology that appears semantically plausible may not contain the relational structures needed for actual decision making. We present OaK, an ontology-as-a-kernel framework that dynamically constructs and refines task-oriented ontologies for LLM agents. Given task requirements and training data, OaK constructs an ontology and its knowledge graph, generates task-adaptation functions for graph reasoning, and uses judge feedback to iteratively refine both. By making relevant concepts and relations explicit, the ontology grounds knowledge retrieval and multi-step decision making. We evaluate OaK on TravelPlanner, CRMArenaPro, and ToolQA. Results show that OaK improves standard LLM agents, strengthens evidence grounding, and boosts the reliability of multi-step reasoning.
