Story
arxiv_cs_cl ยท Oct 22, 2026 ยท paper
Source brief
Beyond Watching and Searching: Benchmarking Agents for Video-centered Deep Research Reports
arxiv.orgOct 22, 2026
original source linked
In brief
Deep research agents synthesize open-web evidence into long reports, but current benchmarks do not evaluate research centered on a source video. We introduce Video-Centered Deep Research Report Generation. Given a vid...
Feed lens
agentharnessevaluation