STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability Paper • 2606.19236 • Published 3 days ago • 8
RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation Paper • 2605.13542 • Published May 13 • 8
MedOpenClaw: Auditable Medical Imaging Agents Reasoning over Uncurated Full Studies Paper • 2603.24649 • Published Mar 25 • 31