# C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning

arXiv: https://arxiv.org/abs/2605.27860 · HTML: https://mlsanity.com/paper/2605.27860/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 19 of its 48 references that are in the map.
- First posted on arXiv 27 May 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- Retrieval-augmented generation / [Medical and biomedical RAG](https://mlsanity.com/rag/medical-and-biomedical-rag/)

## Builds on (most cited first, 19 of 19)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding](https://mlsanity.com/paper/2501.18362/) (2025)
- [Med42-v2: A Suite of Clinical LLMs](https://mlsanity.com/paper/2408.06142/) (2024)
- [Baichuan-M2: Scaling Medical Capability with Large Verifier System](https://mlsanity.com/paper/2509.02208/) (2025)
- [Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents](https://mlsanity.com/paper/2510.14967/) (2025)
- [MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning](https://mlsanity.com/paper/2506.00555/) (2025)
- [R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning](https://mlsanity.com/paper/2506.04185/) (2025)
- [Supervising the search process produces reliable and generalizable information-seeking agents](https://mlsanity.com/paper/2502.13957/) (2025)
- [R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning](https://mlsanity.com/paper/2505.23794/) (2025)
- [EHR-R1: A Reasoning-Enhanced Foundational Language Model for Electronic Health Record Analysis](https://mlsanity.com/paper/2510.25628/) (2025)
- [End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning](https://mlsanity.com/paper/2508.15746/) (2025)
- [ProRAG: Process-Supervised Reinforcement Learning for Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.21912/) (2026)
- [Med-R3: Enhancing Medical Retrieval-Augmented Reasoning of LLMs via Progressive Reinforcement Learning](https://mlsanity.com/paper/2507.23541/) (2025)
- [UR2: Unify RAG and Reasoning through Reinforcement Learning](https://mlsanity.com/paper/2508.06165/) (2025)

## Abstract (arXiv)

Retrieval-augmented generation (RAG) trained with reinforcement learning (RL) is a promising way to ground large language models in medical evidence for clinical diagnosis. However, existing RAG-RL methods face two problems: (1) their process reward is largely singleview, as most methods inherited from opendomain multi-hop QA reward only the quality of the retrieved information; (2) assigning a reliable process reward is hard, as hard matching gives zero to clinically correct but non-verbatim steps such as "Allergic Sinusitis" versus "Allergic Rhinitis", and the alternative of strong-teacher guiding is bounded by the teacher's own medical competence. To address these issues, we propose C-MIG, a Multiview Information Gain-based framework for Clinical diagnosis. We identify two complementary and crucial intermediate steps in clinical diagnosis: what to retrieve and how to refine. We reward both by the information gain each brings, measured as the increase in the predicted likelihood of the ground-truth answer under a base, frozen reference model. The frozen scorer yields a stable and reproducible reward that needs no extra reward model or teacher. Experiments on four medical benchmarks show that C-MIG outperforms RAGRL baselines in and out of domain and stays competitive with far larger medical-specialist and general-purpose LLMs, at only about 3.4% training overhead and no inference-time cost.