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

Agent Task and Scenario Completion on AppWorld (dev)

89.5Task Goal Completion

Trajectory-Informed Memory Generation

76.70880.02983.3586.671Mar 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
89.573.7
2026.03
77.247.4