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

ARMMAN

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multi-agent ReasoningARMMAN
Accuracy85.78
9
User Engagement OptimizationARMMAN real-world data (Budget 4%)
Mean Weekly Engagement Improvement458.1
3
User Engagement OptimizationARMMAN real-world data Budget 2% (Evaluation Method 1)
Mean Weekly Engagement Improvement362.5217
3
Maternal Healthcare Engagement OptimizationARMMAN real-world data
Mean Weekly Engagement Improvement424.0043
3
Showing 4 of 4 rows