# MedEvo：通过知识导航实现医学推理进化

> 原文链接：https://robotics.hellobike.com/papers/2026-10-13-2610-17690
> 频道：papers | 更新日期：2026-10-13 | 标签：arxiv, cs.RO
> 核心摘要：MedEvo用医学标签体系与错误诊断修复失败轨迹并选择数据，在七个基准及MedXpertQA-MM上验证提升准确率。

# MedEvo：通过知识导航实现医学推理进化

::: v-pre
> 原文链接：[MedEvo: Medical Reasoning Evolution through Knowledge Navigation](https://arxiv.org/abs/2610.17690)（arXiv 2610.17690 · 发布日期：2026-10-13）

**MedEvo: Medical Reasoning Evolution through Knowledge Navigation**

MedEvo用医学标签体系与错误诊断修复失败轨迹并选择数据，在七个基准及MedXpertQA-MM上验证提升准确率。

## 核心要点

- 现有医学多模态推理训练常丢弃学生失败轨迹中的有效推理。
- MedEvo以医学标签分类体系和错误类型诊断引导修复与数据选择。
- 审查器定位首个关键错误并给无答案提示，学生保留有效前缀再生成。
- 仅用SFT，Qwen3.5-9B七基准均值准确率由65.57%升至69.12%。

**验证范围与局限**：验证范围为七个基准及MedXpertQA-MM多模态赛道上的准确率评测。

## 英文摘要 (Abstract)

Medical multimodal reasoning models are typically trained on teacher-generated rationales, discarding the valid reasoning in students' own failed trajectories, while general-domain correction methods offer little guidance for errors in image reading, anatomical context, or differential diagnosis. We propose MedEvo, which uses medical knowledge, namely a tag taxonomy and error-type diagnosis, to navigate both trajectory repair and data selection. For each failed rollout, a gold-blind auditor locates the first consequential error and provides a minimal, answer-free hint; the same student retains the valid prefix and regenerates the erroneous suffix. After each round, MedEvo identifies capability gaps across medical tags on a held-out feedback set and prioritizes related questions for new rollouts and repairs. With supervised fine-tuning (SFT) alone, MedEvo raises Qwen3.5-9B mean accuracy across seven benchmarks from 65.57% to 69.12% (47.40% to 54.50% on the multimodal track of MedXpertQA (MedXpertQA-MM)), surpassing teacher-distillation SFT (66.93%). It also raises Qwen3.5-35B and Qwen3.5-397B mean accuracy from 67.91% to 73.04% and from 71.83% to 74.95%, respectively. Our analyses show that failed trajectories contain reasoning worth preserving, that repair success does not imply learning value, and that independent feedback is key to sustained improvement.

作者：Xiaoliang Wang, Zhuo Chen, Chuanyang Zheng, Quanbin Wang, Jiangwei Lao, Yingao Liu, Jiajia Liu, Jinming Cao, Honglin Lin, Zhihong Lu
:::

## 原始参考来源 (Sources)

- [arXiv 2610.17690：MedEvo: Medical Reasoning Evolution through Knowledge Navigation](https://arxiv.org/abs/2610.17690)