← back
arXivHebin Hu, Renke Dai, Ah-Hwee Tan, Yilin KangTue, May 19, 2026, 5:38 AM PDT
score 16.3

New benchmark tests AI healthcare agents on patient history recall

Original: Synthesis and Evaluation of Long-term History-aware Medical Dialogue

Source: arxiv.org

Writing ELI5 summary…