MedS$^3$: Towards Medical Slow Thinking with Self-Evolved Soft Dual-sided Process Supervision

Understand

Medical language models face critical barriers to real-world clinical reasoning applications.

• However, mainstream efforts, which fall short in task coverage, lack fine-grained supervision for intermediate reasoning steps, and rely on proprietary systems, are still far from a versatile, credible and efficient language model for clinical reasoning usage.
• To this end, we propose MedS3, a self-evolving framework that imparts robust reasoning capabilities to small, deployable models.
• Starting with 8,000 curated instances sampled via a curriculum strategy across five medical domains and 16 datasets, we use a small base policy model to conduct Monte Carlo Tree Search (MCTS) for constructing rule-verifiable reasoning trajectories.