具身开发者社区

外观

论文arXiv 2610.1681116 天前

X-Ragent：用于证据支撑胸部X光推理的工具增强强化学习 ​

X-Ragent通过工具增强强化学习选择性获取辅助证据和有效测量，并在三个CXR基准上验证胸部X光证据支撑推理。

AI 整理
  • 具身模型
  • 评测与安全

原文链接：X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoning（arXiv 2610.16811 · 发布日期：2026-10-12）

X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoning

X-Ragent通过工具增强强化学习选择性获取辅助证据和有效测量，并在三个CXR基准上验证胸部X光证据支撑推理。

核心要点 ​

  • CXR解读需结合视觉发现与任务证据，现有工具代理缺少取证时机与无效测量过滤机制。
  • X-Ragent解耦辅助证据寻求与有效性门控定量测量获取。
  • 用7.7K样本Rad-CoT初始化Qwen3-VL-8B，并以GRPO优化策略。
  • 在三个CXR基准取得最强结果，ChestAgentBench提升8.6点。

验证范围与局限：验证范围为三个CXR基准，包含完全留出的ChestAgentBench。

英文摘要 (Abstract) ​

Chest X-ray (CXR) interpretation often requires integrating visual findings with task-specific evidence rather than relying on direct visual recognition alone. While tool-augmented medical agents can supply such evidence via external modules, they often lack explicit mechanisms for learning when auxiliary evidence is needed and for preventing inapplicable quantitative evidence from entering diagnostic reasoning. To address this, we propose X-Ragent, a post-training framework for tool-augmented reinforcement learning that decouples learned auxiliary-evidence seeking from validity-gated quantitative measurement acquisition for evidence-grounded CXR reasoning. We construct Rad-CoT, a 7.7K-sample corpus combining causally ordered tool-augmented trajectories with report-style diagnostic reasoning, and use it to initialize Qwen3-VL-8B via agentic supervised fine-tuning (SFT). We then optimize the policy with Group Relative Policy Optimization (GRPO) using an accuracy-gated reward that applies process-level terms for measurement consistency and auxiliary-tool cost only to correct trajectories, preventing plausible process behavior from compensating for an incorrect diagnosis. Across three CXR benchmarks, X-Ragent achieves the strongest results, including an 8.6-point improvement on the fully held-out ChestAgentBench. By seeking evidence selectively and admitting only valid measurements, X-Ragent supports more faithful and evidence-grounded CXR reasoning.

作者：Yi Wang, Zhenlong Yuan, Yuchan Guo, Maolei Huang, Zijian Song, Dapeng Zhang, Rongbin Tan, Jiyuan Wang, Zhiyuan Wang, Fangfang Lin

来源

本页事实对应的公开页面，以原文为准。

  1. arXiv 2610.16811：X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoning访问 2026-10-21