FoG：训练知识图谱智能体检索答案背后的证据
Clearing the FoG: Training KG Agents to Retrieve the Evidence Behind Their Answers
AI 导读
arXiv 论文提出 FoG 框架，训练知识图谱（KG）智能体检索支撑其答案的证据三元组，而非仅把 KG 当作答案来源。FoG 包含证据扎根的数据合成、KG 交互智能体和证据覆盖过程奖励（ECPR）。在三个 KGQA 基准上，3B–4B 开源模型在答案准确率和证据覆盖率上显著超越更大规模的基线，并具备零样本跨 KG 迁移能力。
正文 · 原文
Abstract:Large language models (LLMs) can answer many factual questions correctly, but a correct answer is not necessarily a supported one. For an LLM agent, a knowledge graph (KG) plays two roles: as a source of answers, it supplies facts that the model lacks; as a source of evidence, it supplies the supporting triples that make an answer traceable and auditable. However, existing KG agents treat the KG only as a source of answers: their training data carries answers but not evidence, and their training rewards check the answer but not the retrieved evidence, so agents often answer correctly without retrieving the supporting triples. We propose FoG, a framework that trains KG agents to retrieve the evidence behind their answers. FoG consists of evidence-grounded synthesis, a KG interaction agent, and an evidence-coverage process reward (ECPR): the synthesis recursively hides explicit entities behind verifiable sub-questions, so that every question carries its supporting triples by construction; the agent records the triples returned by the KG; and ECPR credits each supporting triple to the turn that first retrieves it. Experiments on three KGQA benchmarks demonstrate that FoG enables 3B--4B open-source agents to outperform substantially larger baselines in answer accuracy and evidence coverage, with zero-shot cross-KG transfer.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.37405 [cs.AI] |
| (or arXiv:2610.37405v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37405 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zongyuan Sun [view email]
[v1]
Tue, 27 Oct 2026 15:20:37 UTC (6,551 KB)
来源：arXiv cs.AI · arxiv.org