Share your thoughts, 1 month free Claude Pro on usSee more

Agentic Task Solving on EHRCon

79.1Pass@3

RetroAgent

Updated 23d ago

Evaluation Results

Method	Links
RetroAgent 2026.05		79.1	85.2
GiGPO 2026.05		78.1	83.3
ReACT 2026.05		77.2	83.3
A³ 2026.05		77.2	79.6
A³ 2026.05		75	79.6
HGPO 2026.05		71.1	75.9
GSPO 2026.05		68.9	75.9
rStar 2026.05		63.3	70.4
LATS 2026.05		61.7	70.4