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

Hugging Face Daily Papers Papers
medical-ai reinforcement-learning chest-x-ray tool-augmented-agents multimodal-llm grpo vision-language-model

Summary

X-Ragent 是一个面向胸片（CXR）证据驱动推理的后训练框架，通过工具增强强化学习解耦辅助证据获取与有效性门控的量化测量；在 Chest AgentBench 等三个基准上取得最佳结果，其中完全未见基准提升 8.6 分。

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.
Original Article
View Cached Full Text

Cached at: 10/14/26, 06:53 AM

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

Source: https://huggingface.co/papers/2610.16811 Authors:

,

,

,

,

,

,

,

,

,

,

Abstract

ChestX-ray(CXR)interpretationoftenrequiresintegratingvisualfindingswithtask-specificevidenceratherthanrelyingondirectvisualrecognitionalone.Whiletool-augmentedmedicalagentscansupplysuchevidenceviaexternalmodules,theyoftenlackexplicitmechanismsforlearningwhenauxiliaryevidenceisneededandforpreventinginapplicablequantitativeevidencefromenteringdiagnosticreasoning.Toaddressthis,weproposeX-Ragent,apost-trainingframeworkfortool-augmentedreinforcementlearningthatdecoupleslearnedauxiliary-evidenceseekingfromvalidity-gatedquantitativemeasurementacquisitionforevidence-groundedCXRreasoning.WeconstructRad-CoT,a7.7K-samplecorpuscombiningcausallyorderedtool-augmentedtrajectorieswithreport-stylediagnosticreasoning,anduseittoinitializeQwen3-VL-8Bviaagenticsupervisedfine-tuning(SFT).WethenoptimizethepolicywithGroupRelativePolicyOptimization(GRPO)usinganaccuracy-gatedrewardthatappliesprocess-leveltermsformeasurementconsistencyandauxiliary-toolcostonlytocorrecttrajectories,preventingplausibleprocessbehaviorfromcompensatingforanincorrectdiagnosis.AcrossthreeCXRbenchmarks,X-Ragentachievesthestrongestresults,includingan8.6-pointimprovementonthefullyheld-outChestAgentBench.Byseekingevidenceselectivelyandadmittingonlyvalidmeasurements,X-Ragentsupportsmorefaithfulandevidence-groundedCXRreasoning.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2610\.16811

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.16811 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.16811 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.16811 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography

Hugging Face Daily Papers

RadAgent is a tool-using AI agent that generates chest CT reports through interpretable step-by-step reasoning, improving clinical accuracy by 36.4% relative and achieving 37% faithfulness—a capability absent in existing 3D vision-language models. The system provides fully inspectable reasoning traces allowing clinicians to validate and refine diagnostic outputs.

Reasoning-Informed Visual Editing

Hugging Face Daily Papers

该论文提出了 RISEBench 及其扩展版本 RISEBench++，这是首个评估推理驱动视觉编辑（Reasoning-Informed Visual Editing）的基准，涵盖时序、因果、空间、逻辑、反事实及混合推理等六个维度，并提出训练无关的 RISE-Agent 框架，结果显示即使是 GPT-Image-2.5 Sunburst 也仅达 56.6% 准确率。

From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoning

Hugging Face Daily Papers

该论文提出CASE——一系列用于证据搜集的临床智能体，结合工具使用框架与智能体后训练方法，在基于UK Biobank构建的纵向多模态医学基准上进行评估，其基于Qwen3-VL-8B的智能体在匹配评估条件下答案准确率相对GPT-5.4和Claude Opus 4.8分别提升超16%和10%。