MedEvo: Medical Reasoning Evolution through Knowledge Navigation

cs.AI, cs.CV, cs.LG, q-bio.QM

Submitted: 2026-10-13

Updated: 2026-10-13

Comments: Project: https://pork-pay.github.io/MedEvo/; GitHub: https://github.com/pork-pay/MedEvo

Code: https://github.com/pork-pay/MedEvo

Project page: https://pork-pay.github.io/MedEvo

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Hindsight Hint Distillation: Scaffolded Reasoning for SWE Agents from CoT-free Answers
• Learning From Mistakes Makes LLM Better Reasoner
• Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
• Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
• Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning
• BiMediX2: Bio-Medical EXpert LMM for Diverse Medical Modalities
• MedGemma Technical Report
• Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey
• Disentangling Reasoning and Knowledge in Medical Large Language Models
• Better Accuracies, Worse Reasoning: A Step-Level Audit of Medical Chain-of-Thought Distillation
• When Rubrics Fail: Hallucinations Reveal Blind Spots in Medical AI Evaluation
• A Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and Teaching
• Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation
• Selective Regenerative Decoding: Trajectory-Level Intervention for Inference-Time Reasoning
• Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight
• Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation
• MediSkill-Evo: Process-Constrained Self-Evolution for Evidence-Grounded Clinical Interaction
• Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI
• Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems