End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Qiaoyu, Sun, Yuze, Wu, Chaoyi, Zhao, Weike, Qiu, Pengcheng, Yu, Yongguo, Sun, Kun, Zhang, Jian, Wang, Yanfeng, Zhang, Ya, Xie, Weidi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910007062167552
author Zheng, Qiaoyu
Sun, Yuze
Wu, Chaoyi
Zhao, Weike
Qiu, Pengcheng
Yu, Yongguo
Sun, Kun
Zhang, Jian
Wang, Yanfeng
Zhang, Ya
Xie, Weidi
author_facet Zheng, Qiaoyu
Sun, Yuze
Wu, Chaoyi
Zhao, Weike
Qiu, Pengcheng
Yu, Yongguo
Sun, Kun
Zhang, Jian
Wang, Yanfeng
Zhang, Ya
Xie, Weidi
contents The integration of Large Language Models (LLMs) into healthcare is constrained by knowledge limitations, hallucinations, and a disconnect from Evidence-Based Medicine (EBM). While Retrieval-Augmented Generation (RAG) offers a solution, current systems often rely on static workflows that miss the iterative, hypothetico-deductive reasoning of clinicians. To address this, we introduce Deep-DxSearch, an agentic RAG system trained end-to-end via reinforcement learning (RL) for traceable diagnostic reasoning. Deep-DxSearch acts as an active investigator, treating the LLM as an agent within an environment of 16,000+ guideline-derived disease profiles, 150,000+ patient records for case-based reasoning, and over 27 million biomedical documents. Using soft verifiable rewards that co-optimize retrieval and reasoning, the model learns to formulate queries, evaluate evidence, and refine searches to close diagnostic gaps. Experiments show our end-to-end RL framework consistently outperforms prompt-engineering and training-free RAG methods. On in-distribution (ID) and out-of-distribution (OOD) benchmarks for common and rare diseases, Deep-DxSearch surpasses strong baselines-including GPT-4o, DeepSeek-R1, and medical-specific frameworks-achieving an average accuracy gain of 22.7% over the second-best model. In validation with 150 real-world cases, Deep-DxSearch boosts physicians' average diagnostic accuracy from 45.6% to 69.1%. These results indicate that evolving agentic systems to leverage statistical regularities in large-scale healthcare data is key for trustworthy diagnostic assistants. All data, code, and checkpoints are available at https://qiaoyu-zheng.github.io/Deep-DxSearch.
format Preprint
id arxiv_https___arxiv_org_abs_2508_15746
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning
Zheng, Qiaoyu
Sun, Yuze
Wu, Chaoyi
Zhao, Weike
Qiu, Pengcheng
Yu, Yongguo
Sun, Kun
Zhang, Jian
Wang, Yanfeng
Zhang, Ya
Xie, Weidi
Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
The integration of Large Language Models (LLMs) into healthcare is constrained by knowledge limitations, hallucinations, and a disconnect from Evidence-Based Medicine (EBM). While Retrieval-Augmented Generation (RAG) offers a solution, current systems often rely on static workflows that miss the iterative, hypothetico-deductive reasoning of clinicians. To address this, we introduce Deep-DxSearch, an agentic RAG system trained end-to-end via reinforcement learning (RL) for traceable diagnostic reasoning. Deep-DxSearch acts as an active investigator, treating the LLM as an agent within an environment of 16,000+ guideline-derived disease profiles, 150,000+ patient records for case-based reasoning, and over 27 million biomedical documents. Using soft verifiable rewards that co-optimize retrieval and reasoning, the model learns to formulate queries, evaluate evidence, and refine searches to close diagnostic gaps. Experiments show our end-to-end RL framework consistently outperforms prompt-engineering and training-free RAG methods. On in-distribution (ID) and out-of-distribution (OOD) benchmarks for common and rare diseases, Deep-DxSearch surpasses strong baselines-including GPT-4o, DeepSeek-R1, and medical-specific frameworks-achieving an average accuracy gain of 22.7% over the second-best model. In validation with 150 real-world cases, Deep-DxSearch boosts physicians' average diagnostic accuracy from 45.6% to 69.1%. These results indicate that evolving agentic systems to leverage statistical regularities in large-scale healthcare data is key for trustworthy diagnostic assistants. All data, code, and checkpoints are available at https://qiaoyu-zheng.github.io/Deep-DxSearch.
title End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning
topic Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.15746