- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes X-Ragent, a tool-augmented reinforcement learning framework for evidence-grounded chest X-ray reasoning. It introduces Rad-CoT, a 7.7K-sample corpus of diagnostic reasoning trajectories, and combines agentic SFT with GRPO and accuracy-gated rewards. The method achieves strong results across three CXR benchmarks.
Critical strengths
-
The motivation is reasonable, and the proposed corpus provides useful supervision for tool use and evidence-grounded reasoning.
-
The method achieves strong results across three benchmarks.
Critical weaknesses
-
The novelty is limited, as the method primarily combines existing techniques, including SFT, GRPO, and tool augmentation.
-
Ablation results suggest that the gains from RL over SFT are relatively modest, raising questions about the necessity and contribution of RL to the overall performance.
-
Rad-CoT relies on LLM-generated reasoning trajectories filtered by rule-based checks, leaving their reliability insufficiently validated.
-
The baseline comparison is insufficient, with limited coverage of recent medical VLMs and tool-augmented reasoning agents.
Questions for authors
-
What is the substantive methodological novelty of X-Ragent compared with existing approaches?
-
How do the authors validate the reliability of the LLM-generated reasoning trajectories in Rad-CoT?
-
How does X-Ragent compare with recent medical VLMs and tool-augmented reasoning methods?
4 comments
W3 / Q2: How is Rad-CoT reliability validated beyond rule-based filtering?
A3: We add reference-report claim audits and independent medical-model screening:
| Report-style audit | Result |
|---|---|
| Randomly sampled trajectories | 400/4,000 |
| Claims supported by reference Findings | 97.3% |
| Contradicted / indeterminate claims | 0.6% / 2.1% |
| Trajectories with no detected contradiction | 97.5% |
The audit detects 49/50 (98.0%) separately constructed contradictions involving disease presence, laterality, location, and severity. For 300/3,715 task-stratified routed trajectories, Lingshu-7B, distinct from the generation teacher, checks the CXR, ground-truth answer, and evidence, flagging 9 (3.0%). The audit permits image-based corrections to tool observations.
Rad-CoT contains 4,000 report-style trajectories generated by Qwen3.5-122B-A10B-FP8 from CXRs and reference Findings, retaining Findings as targets, plus 3,715 QA-derived routed trajectories with ground-truth answers and actual tool observations. Calls precede observations; teacher rescreening and format, length, similarity, and leakage filtering follow. The sampled claims' reference support and independent screening provide content-level evidence for supervision reliability beyond formatting checks.
W4 / Q3: How does X-Ragent compare with recent medical VLMs and agents?
A4: We add [CheXOne (Zhang et al., 2026)], [Lingshu-7B (Xu et al., 2025)], and mechanism adaptations of [ViTAR (Chen et al., 2025)] and [Ophiuchus (Jiang et al., ICML 2026)], whose preprint appeared in 2025.
| Method | ChestAgentBench (%) | CheXbench (%) |
|---|---|---|
| CheXOne | 58.72 | 71.27 |
| Lingshu-7B | 63.60 | 63.59 |
| ViTAR-style | 67.8 | 73.5 |
| Ophiuchus-inspired | 70.3 | 75.8 |
| X-Ragent | 71.7 | 77.3 |
ChestAgentBench uses all 2,500 questions; CheXbench is the macro-average over three sources. CheXOne and Lingshu-7B use direct inference. ViTAR-style shares Qwen3-VL-8B-Instruct, CXR training tasks, and evaluation, retaining region marking, two-turn reinspection, and SFT/GRPO. Ophiuchus-inspired shares Rad-CoT SFT initialization, tool interfaces, and GRPO configuration, using its VQA-conditioned tool reward without self-reflection SFT. These are controlled mechanism adaptations, not full reproductions of the original methods.
X-Ragent gains 3.9/3.8 pp over ViTAR-style and 1.4/1.5 pp over Ophiuchus-inspired. Against the latter on ChestAgentBench, invocation rate drops from 93.1% to 53.2%, calls from 1.52 to 0.95/question (−37.5%), and latency from 15.8 to 12.4 s/question (−21.5%). Invocation rate counts questions with any call; averages use all questions.
Apologies for the delayed response. I've been quite busy recently.
Thank you for the rebuttal. However, even after the authors' explanations, I still don't quite see the novelty and significance of this work. I also don't find the significant performance gains over the newly added baselines. Currently, I will maintain my rating.
Thank you for clarifying your remaining concerns. We would like to explain more concretely the design contribution and the evidence supporting its value.
1. What does X-Ragent contribute?
X-Ragent separates two decisions that require different criteria. The policy learns which auxiliary information is useful for a question, including regional inspection, crops, and disease knowledge. A separate backend determines whether quantitative measurements are applicable based on projection and anatomical geometry, and supplies eligible measurements without requiring a policy call. For example, a question may concern heart size, while the image projection makes CTR unsuitable for interpretation.
Training follows this separation. Visual and knowledge tool use is optimized through answer performance. Measurement interpretations additionally receive consistency supervision against backend values, categories, and directions. Both measurement-consistency credit and auxiliary-call cost apply only to correctly answered trajectories. Rad-CoT provides causally ordered tool calls, actual observations, and diagnostic reasoning for learning this behavior.
SFT, GRPO, and correctness-conditioned rewards are established techniques. Our methodological contribution is the specific coordination of learned evidence acquisition, independent measurement applicability checks, and measurement-consistency supervision.
2. What demonstrates its practical significance?
The added comparisons show benefits in both accuracy and computational cost. X-Ragent exceeds ViTAR-style by 3.9/3.8 pp on ChestAgentBench/CheXbench. Against the closer Ophiuchus-inspired adaptation, it gains 1.4/1.5 pp while using 37.5% fewer auxiliary calls and 21.5% less end-to-end time on ChestAgentBench. The latter comparison shares the backbone, Rad-CoT SFT initialization, tool interfaces, and GRPO configuration, using the Ophiuchus-inspired tool reward without its self-reflection SFT. These results evaluate the specified CXR adaptations.
Further controls help identify where the benefit comes from. With the same checkpoint, toolbox, and 0.95 calls/question, learned routing reaches 71.7%, compared with 69.3% for budget-matched random routing. Relative to Static-All, it reduces latency by 35.1% and GPU-seconds by 35.8%, with observed accuracies of 71.7% and 71.0%. Separately, the Gate rejects 379/400 AP or lateral inputs in projection validation, directly supporting its role in screening measurement applicability.
Together, these experiments support the value of the proposed design through component gains, question-dependent tool selection, and lower inference cost.
Thank you for reviewing our work and for your suggestions on methodological contribution and data reliability. We hope these additions answer your questions; following your feedback, we will refine the relevant material and upload a revised manuscript.
A1: We do not claim SFT, GRPO, learned tool calling, or correctness conditioning alone as novel. X-Ragent organizes evidence acquisition, applicability checks, and diagnostic process supervision around the different degrees of evidence verifiability.
Separate acquisition from applicability. Parsing, cropping, and disease knowledge have question-dependent value and are selected by the policy. CTR, LFA, and Thoracic Shift depend on projection and anatomical geometry; a separate backend checks these conditions and directly supplies accepted measurements without a policy-selected measurement call.
Supervise what can be checked. Visual/knowledge use is optimized through final task performance. Eligible measurements additionally permit checks of value, category, and direction interpretation against backend outputs. We combine this task-relevant
R_CXRwith auxiliary-call cost:R(τ)=Rformat+Racc(1+λmRCXR−λtRtool)
Only correct answers receive measurement-consistency credit; call cost discourages unnecessary acquisition. Rad-CoT's causally ordered calls, actual observations, and diagnoses align supervision with this architecture. The design explicitly controls both evidence admissibility and interpretation, extending beyond tool selection alone. Corresponding controls are:
These controls separately support the pathway, supervision, and reward design, providing component evidence for the methodological contribution. Reply 2/2 includes recent-agent comparisons.
A2: With the same tools, Measurement Gate, and inference protocol, RL improves held-out ChestAgentBench accuracy by 3.1 pp:
Tool-free results are from Table 2; evaluating the SFT checkpoint with the same tools is an additional experiment. ChestAgentBench is excluded from post-training in both settings. Table 3 further shows that the full reward exceeds Answer + Format Reward by 2.3 pp (69.4%→71.7%) and the ungated combination by 1.9 pp. RL therefore improves the capabilities established by SFT even when tool access is held fixed.