# CXReasonAgent: Evidence-Grounded Diagnostic Reasoning Agent for Chest X-rays

Source: [CXReasonAgent: Evidence-Grounded Diagnostic Reasoning Agent for Chest X-rays](<https://www.sota2.com/research/paper/69a1251b2d603e6de3e3c625>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-26T05:00:04.121Z

Authors: Hyungyung Lee, Hangyul Yoon, Edward Choi

Published: 2026-02-26T17:51:21.000Z

## Abstract

Chest X-ray plays a central role in thoracic diagnosis, and its interpretation inherently requires multi-step, evidence-grounded reasoning. However, large vision-language models (LVLMs) often generate plausible responses that are not faithfully grounded in diagnostic evidence and provide limited visual evidence for verification, while also requiring costly retraining to support new diagnostic tasks, limiting their reliability and adaptability in clinical settings. To address these limitations, we present CXReasonAgent, a diagnostic agent that integrates a large language model (LLM) with clinically grounded diagnostic tools to perform evidence-grounded diagnostic reasoning using image-derived diagnostic and visual evidence. To evaluate these capabilities, we introduce CXReasonDial, a multi-turn dialogue benchmark with 1,946 dialogues across 12 diagnostic tasks, and show that CXReasonAgent produces faithfully grounded responses, enabling more reliable and verifiable diagnostic reasoning than LVLMs. These findings highlight the importance of integrating clinically grounded diagnostic tools, particularly in safety-critical clinical settings. The demo is available \\href{https://ttumyche.github.io/cxreasonagent/#demo}{here}.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Evidence-Grounded Diagnostic Reasoning on CXReasonDial](<https://www.sota2.com/research/sota/evidence-grounded-diagnostic-reasoning-on-cxreasondial.md>): Evidence-grounded diagnostic reasoning; CXReasonDial; Coverage: 99.7.

- [Evidence-grounded diagnostic reasoning on CXReasonDial Dynamic User Simulator](<https://www.sota2.com/research/sota/evidence-grounded-diagnostic-reasoning-on-cxreasondial-dynamic-user-simulator.md>): Evidence-grounded diagnostic reasoning; CXReasonDial Dynamic User Simulator; Coverage (Cov): 99.9.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.23276>)

[PDF](<https://arxiv.org/pdf/2602.23276.pdf>)