arXiv cs.AI· Zhisheng Qi, Haoyu Han, Jiaxi Li, Bing He, Huiyuan Chen, Franck Dernoncourt, Ryan A. Rossi, Mahantesh M. Halappanavar, Jin Lu, Yu Zhang, Tianming Liu, Yu Wang·· 3 天前AI 评分27
CoRE：面向结构化知识检索的协同自适应规则路由与约束
Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval
AI 导读
针对结构化知识检索中预定义查询-规则监督难以获取的问题，研究者提出 CoRE，让路由智能体为每个查询选择推理规则，对应检索器再在该规则约束下遍历知识库并排序证据。CoRE 交替使用强化学习训练路由策略、对比学习训练规则约束检索器，形成无需显式查询-规则标注的闭环协同。在 STaRK-QA 的科学发现、生物医学推理和电商知识管理数据集上，实验与消融验证了协同自适应的有效性，生成式路由可跨数据集迁移。
正文 · 原文
Authors:Zhisheng Qi, Haoyu Han, Jiaxi Li, Bing He, Huiyuan Chen, Franck Dernoncourt, Ryan A. Rossi, Mahantesh M. Halappanavar, Jin Lu, Yu Zhang, Tianming Liu, Yu Wang
Abstract:Structured knowledge retrieval acquires task-relevant evidence from structured knowledge sources for downstream tasks. Existing methods rely on unconstrained retrieval or predefined query-rule supervision, such as author-paper rules for scientific discovery and anatomy-drug rules for precision medicine. Such supervision is rarely available in practice. We propose Co-Adaptive Rule Routing and Constraining Retrieval (CoRE), which jointly learns which reasoning rule to assign to each query and how to retrieve evidence under that rule, without predefined query-rule pairs. A routing agent selects a rule, and its corresponding retriever traverses the knowledge base and ranks evidence that satisfies the rule's constraints. Because routing and retrieval are interdependent, CoRE alternates between reinforcement learning for the routing policy and contrastive learning for the rule-constrained retriever. The selected rules provide supervision for retriever training, while retrieval performance rewards the routing policy. This closed-loop process enables both components to co-adapt without explicit query-rule supervision. Experiments on STaRK-QA datasets across scientific discovery, biomedical reasoning, and e-commerce knowledge management demonstrate CoRE's effectiveness. Ablations show the benefit of co-adapting the router and retriever. Generation-based routing transfers across datasets and benefits from multi-domain pretraining followed by target-specific fine-tuning. Analysis of rule usage across queries also informs automatic rule refinement and discovery.
| Comments: | Under review at ICLR |
| Subjects: | Information Retrieval (cs.IR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.14465 [cs.IR] |
| (or arXiv:2610.14465v1 [cs.IR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.14465 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhisheng Qi [view email]
[v1]
Sat, 10 Oct 2026 01:45:48 UTC (2,786 KB)
来源：arXiv cs.AI · arxiv.org