Multi-agent coordination
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
67Task Success Rate
24
May 14, 2026
1Task Success Rate
24
May 14, 2026
4.19Task Score
24
May 14, 2026
4.5Task Score (PP-O Ablation)
24
May 14, 2026
2.43Task Metric Value
24
May 14, 2026
0Collisions
24
May 14, 2026
0Collisions
24
May 14, 2026
100Average Win Rate
24
Apr 1, 2026
182.7Self-Play Score
16
Jun 9, 2026
65Win Rate
16
Apr 1, 2026
46Average Win Rate
16
Apr 1, 2026
77Average Win Rate
16
Apr 1, 2026
100Max Success Rate
15
Jun 8, 2026
100Success Rate
13
Jun 9, 2026
80Success Rate
13
Jun 9, 2026
38.1Success Rate
13
May 27, 2026
53.57Success Rate
13
May 27, 2026
307.7Mean Reward
12
May 18, 2026
41.3Average Return
10
May 19, 2026
0Success Rate (Greedy Policy)
10
May 11, 2026
100Success Rate (Greedy Policy pi*)
10
May 11, 2026
39Median Win Rate
10
May 6, 2026
39Median Win Rate
10
May 6, 2026
122.3Coordination Ring Score
10
Apr 2, 2026
2,110Reward
9
Jun 30, 2026