# Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval

arXiv: https://arxiv.org/abs/2610.14465 · HTML: https://mlsanity.com/paper/2610.14465/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 10 Oct 2026.

## Builds on (most cited first, 26 of 26)

- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning](https://mlsanity.com/paper/2310.01061/) (2023)
- [A Review of Relational Machine Learning for Knowledge Graphs](https://mlsanity.com/paper/1503.00759/) (2015)
- [R-Zero: Self-Evolving Reasoning LLM from Zero Data](https://mlsanity.com/paper/2508.05004/) (2025)
- [LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain](https://mlsanity.com/paper/2408.10343/) (2024)
- [Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals](https://mlsanity.com/paper/2101.03737/) (2021)
- [AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning](https://mlsanity.com/paper/2406.11200/) (2024)
- [WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model](https://mlsanity.com/paper/2504.21024/) (2025)
- [STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases](https://mlsanity.com/paper/2404.13207/) (2024)
- [A Review of Biomedical Datasets Relating to Drug Discovery: A Knowledge Graph Perspective](https://mlsanity.com/paper/2102.10062/) (2021)
- [Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data](https://mlsanity.com/paper/2602.21320/) (2026)
- [HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases](https://mlsanity.com/paper/2412.16311/) (2024)
- [Knowledge-Aware Query Expansion with Large Language Models for Textual and Relational Retrieval](https://mlsanity.com/paper/2410.13765/) (2024)
- [CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution](https://mlsanity.com/paper/2604.15840/) (2026)
- [Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills](https://mlsanity.com/paper/2512.16301/) (2025)
- [SciSight: Combining faceted navigation and research group detection for COVID-19 exploratory scientific search](https://mlsanity.com/paper/2005.12668/) (2020)
- [Question-Based Retrieval using Atomic Units for Enterprise RAG](https://mlsanity.com/paper/2405.12363/) (2024)
- [Trajectory-wise Control Variates for Variance Reduction in Policy Gradient Methods](https://mlsanity.com/paper/1908.03263/) (2019)
- [Online Bilevel Optimization: Regret Analysis of Online Alternating Gradient Methods](https://mlsanity.com/paper/2207.02829/) (2022)
- [Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases](https://mlsanity.com/paper/2502.20317/) (2025)
- [Reasoning by Exploration: A Unified Approach to Retrieval and Generation over Graphs](https://mlsanity.com/paper/2510.07484/) (2025)
- [Multi-Field Adaptive Retrieval](https://mlsanity.com/paper/2410.20056/) (2024)
- [Enhancing Retrieval Systems with Inference-Time Logical Reasoning](https://mlsanity.com/paper/2503.17860/) (2025)
- [Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval](https://mlsanity.com/paper/2606.04391/) (2026)
- [Alternating Gradient-Type Algorithm for Bilevel Optimization with Inexact Lower-Level Solutions via Moreau Envelope-based Reformulation](https://mlsanity.com/paper/2412.18929/) (2024)

## Abstract (arXiv)

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.