Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

XrayClaw: Cooperative-Competitive Multi-Agent Alignment for Trustworthy Chest X-ray Diagnosis

Shawn Young, Lijian Xu

Abstract

Chest X-ray (CXR) interpretation is a fundamental yet complex clinical task that increasingly relies on artificial intelligence for automation. However, traditional monolithic models often lack the nuanced reasoning required for trustworthy diagnosis, frequently leading to logical inconsistencies and diagnostic hallucinations. While multi-agent systems offer a potential solution by simulating collaborative consultations, existing frameworks remain susceptible to consensus-based errors when instantiated by a single underlying model. This paper introduces XrayClaw, a novel framework that operationalizes multi-agent alignment through a sophisticated cooperative-competitive architecture. XrayClaw integrates four specialized cooperative agents to simulate a systematic clinical workflow, alongside a competitive agent that serves as an independent auditor. To reconcile these distinct diagnostic pathways, we propose Competitive Preference Optimization, a learning objective that penalizes illogical reasoning by enforcing mutual verification between analytical and holistic interpretations. Extensive empirical evaluations on the MS-CXR-T, MIMIC-CXR, and CheXbench benchmarks demonstrate that XrayClaw achieves state-of-the-art performance in diagnostic accuracy, clinical reasoning fidelity, and zero-shot domain generalization. Our results indicate that XrayClaw effectively mitigates cumulative hallucinations and enhances the overall reliability of automated CXR diagnosis, establishing a new paradigm for trustworthy medical imaging analysis.

XrayClaw: Cooperative-Competitive Multi-Agent Alignment for Trustworthy Chest X-ray Diagnosis

Abstract

Chest X-ray (CXR) interpretation is a fundamental yet complex clinical task that increasingly relies on artificial intelligence for automation. However, traditional monolithic models often lack the nuanced reasoning required for trustworthy diagnosis, frequently leading to logical inconsistencies and diagnostic hallucinations. While multi-agent systems offer a potential solution by simulating collaborative consultations, existing frameworks remain susceptible to consensus-based errors when instantiated by a single underlying model. This paper introduces XrayClaw, a novel framework that operationalizes multi-agent alignment through a sophisticated cooperative-competitive architecture. XrayClaw integrates four specialized cooperative agents to simulate a systematic clinical workflow, alongside a competitive agent that serves as an independent auditor. To reconcile these distinct diagnostic pathways, we propose Competitive Preference Optimization, a learning objective that penalizes illogical reasoning by enforcing mutual verification between analytical and holistic interpretations. Extensive empirical evaluations on the MS-CXR-T, MIMIC-CXR, and CheXbench benchmarks demonstrate that XrayClaw achieves state-of-the-art performance in diagnostic accuracy, clinical reasoning fidelity, and zero-shot domain generalization. Our results indicate that XrayClaw effectively mitigates cumulative hallucinations and enhances the overall reliability of automated CXR diagnosis, establishing a new paradigm for trustworthy medical imaging analysis.

Paper Structure

This paper contains 11 sections, 3 equations, 1 figure, 3 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. Cooperative Multi-Agent Diagnostic
  4. Orchestrating Competitive Auditing for CXR Diagnosis
  5. Competitive Preference Optimization
  6. Implementation Details
  7. Experiments
  8. Trustworthy Disease Diagnosis
  9. Faithful Clinical Reasoning
  10. Reliable Domain Generalization
  11. Conclusion

Figures (1)

  • Figure 1: The overarching architecture of XrayClaw. The framework orchestrates a cooperative-competitive alignment process for trustworthy Chest X-ray diagnosis. The Multi Specialized Agents Cooperation pipeline (top) decomposes the diagnostic task into four sequential stages: systematic scanning, targeted lesion analysis, differential reasoning, and structured report synthesis. In parallel, the Omni-Radiologist Agent (bottom) generates a holistic, end-to-end diagnostic output. Through Competitive Preference Optimization, the framework performs a preference comparison between the two pathways, incentivizing the model to favor the rigorous, evidence-based reasoning of the cooperative pipeline over potential hallucinations in the end-to-end output, thereby ensuring clinical trustworthiness.