Nested Browser-Use Learning for Agentic Information Seeking
Open paper
Benchmark
Model
Rank
Results
deep-research-agents-on-browsecomp
NestBrowse-30B-A3B
–
Accuracy: 31.6
deep-research-agents-on-browsecomp-zh
NestBrowse-30B-A3B
–
Accuracy: 42.6
Rank counts only results with a code link.