Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks
Open paper
Benchmark
Model
Rank
Results
deep-research-agents-on-browsecomp-plus
AggAgent (MiniMax-M2.5)
#5
Accuracy: 77.33
deep-research-agents-on-browsecomp
AggAgent (MiniMax-M2.5)
#28
Accuracy: 71.33
Rank counts only results with a code link.