Tag
This survey examines recent progress in medical LLMs, presenting a dual-view approach that connects clinical practice with computational methods, and introduces a benchmark dataset for evaluating medical reasoning capabilities across 18 state-of-the-art models.
EpistemeAI released Reasoning-Medical0.1-27B, a fine-tuned version of Qwen3.5-27B for medical reasoning, claiming to surpass MedGemma on several medical benchmarks by incorporating chain-of-thought reasoning on a curated dataset of 100,000 records.
ArogyaBodha dataset and ArogyaSutra framework enhance multilingual medical reasoning in low-resource settings through diverse data integration and actor-critic multi-agent reasoning.
SEMA-RAG is a self-evolving multi-agent RAG framework for medical question answering that decouples interpretation, exploration, and adjudication into three specialist agents, achieving significant accuracy improvements over baselines across multiple benchmarks.