Multi-agent Simulation
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Multi-agent Simulation averaged across 6 impairment dimensions
100AURC (% of max)
5
Multi-agent Simulation averaged across 6 impairment dimensions
100AURC (% of max)
5
Multi-agent Simulation averaged across 6 impairment dimensions
100AURC (% of max)
5