Author

Xiang Li

Observed name: Li, Xiang

Institutions: Harvard University, Massachusetts General Hospital

Observed institutions: Harvard University, Massachusetts General Hospital

OpenAlex ID: A5151899676

Rewarding Reasoning, Not Answers: Fixing and Bounding Test-Time Reinforcement Learning on Medical QA

2026 · Fan, Kailong, Pu, Anqi, et al. · arXiv (Cornell University)

Works count: 1

Citation count:

H-index:

I10-index: