MedAgentBench-v3 shows capability ceilings and format-knowledge barriers limit pure RL to 18.2% while rule-based SFT reaches 34.1% on clinical protocol tasks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
World Feedback for Clinical Agents: Diagnosing RL in FHIR Environments
MedAgentBench-v3 shows capability ceilings and format-knowledge barriers limit pure RL to 18.2% while rule-based SFT reaches 34.1% on clinical protocol tasks.