Octen-WebGR Collection Generative retrieval for navigational web search: a query is mapped to a URL among up to 196M web pages. • 2 items • Updated 7 days ago • 39
SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents Paper • 2609.08149 • Published Sep 8 • 25
AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities Paper • 2607.13705 • Published Jul 15 • 40