MedEyes: Learning Dynamic Visual Focus for Medical Progressive Diagnosis

ArXi:2511.22018v2 Announce Type: replace-cross Accurate medical diagnosis often involves progressive visual focusing and iterative reasoning, characteristics commonly observed in clinical workflows. While recent vision-language models nstrate promising chain-of-thought (CoT) reasoning capabilities via reinforcement learning with verifiable rewards (RLVR), their purely on-policy learning paradigm tends to reinforce superficially coherent but clinically inaccurate reasoning paths.