Glossary · Term

WideSearch

← all terms

Definition

A benchmark that tests whether AI research agents can pull together broad information across many sources.

A breadth-oriented deep-research evaluation suite emphasizing wide source coverage rather than deep multi-hop reasoning, used alongside BrowseComp and HLE in agent-research benchmarks.

Mentioned in 1 episode

  1. 083
    Training the Translator: How a Small Communication Model Lets Agent Teams Outperform Themselves