arXiv AI
MedEvo: Medical Reasoning Evolution through Knowledge Navigation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Oct 13
MedEvo: Medical Reasoning Evolution through Knowledge Navigation
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...
arXiv AI
Sep 2
HEAL: Hindsight Entropy-Assisted Learning for Reasoning Distillation
arXiv:2603.10359v2 Announce Type: replace Abstract: Distilling reasoning capabilities from Large Reasoning Models (LRMs) into smaller models is typically constrained by the limitations of rejection s...
arXiv AI
Oct 15
Audit Before You Distill: A Controlled Workflow for Reasoning Transfer into Compact Medical Language Models
arXiv:2610.16713v1 Announce Type: cross Abstract: Teacher rationales can help a smaller model answer health professions questions, but they can also reinforce errors. We examined when they help and h...
arXiv Computation and Language
Oct 5
Learning from Repaired Reasoning: Root-Cause-Guided On-Policy Distillation
arXiv:2610.03515v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) uses reference solutions as privileged hindsight to supervise student-generated reasoning trajectories. However, ref...
arXiv Computation and Language
Sep 4
MedQA-MM: Shortcuts Behind Medical Visual Reasoning
The paper introduces MedQA-MM, a benchmark that exposes shortcut reasoning in medical multimodal multiple-choice questions. By auditing prompts, images, and modalities, the authors show that models often rely on textual cues rather than visual evidence, with full-input accuracy at 62.63% but only 5.21% when restricted to text. The study highlights the need for route-level evidence to validate true medical image reasoning.
arXiv AI
Sep 7
Constructing and Evaluating Clinical Reasoning Trajectories for Medical Agent
The paper introduces MedTraj, a framework that constructs, evaluates, and optimizes multi‑step reasoning trajectories for medical AI agents. It parses each trajectory into observations, evidence, numbered steps, and a conclusion, scoring them on coherence, evidence support, hallucination, completeness, and traceability. Experiments on CareQA, PubMedQA, and CECMed show that incorporating quality‑weighted trajectory context improves reasoning coherence and correctness while significantly reducing hallucinations.