List your company

General Instruction Following on WebArena random 100-sample

23Success RateSiRA
11.5614.5317.520.47Jul 31, 2025

Evaluation results

MethodLinks
SiRAReasoning Type=Simulative Reasoning (System II)2025.0723
SiRAReasoning Type=Reactive Policy (System I)2025.0719
OpenHands BrowsingAgent2025.0712