arxivcs.AI2026-07-01
World Feedback for Clinical Agents: Diagnosing RL in FHIR Environments
Ananya Mantravadi, Harshit Rajgarhia, Prasanna Desikan, Abhishek Mukherji
Clinical protocol-execution tasks -- checking a lab value, applying a threshold, placing a correctly structured FHIR order -- are natural candidates for RL from world feedback: once clinical SMEs encode decision logic into a verifier, that verifier grades unlimited rollouts witho…