Meituan LongCat unveils DeepResearch multi-agent system scoring 55.25 on DeepResearchBench

Meituan LongCat Team · hf · 2026-09-30

Meituan's LongCat team presents LongCat-DeepResearch, pairing an enhanced LongCat model with a multi-agent workflow: planning agents build a ResearchSpec, research agents draft sections in parallel in isolated contexts, and section-level revisions replace full-report rewrites. It scores 55.25 on DeepResearchBench, 51.35 on DeepResearchBench II, 79.83 on ResearchRubrics, and 76.04 on an internal benchmark (2nd of 4 systems). The workflow also generates tasks and trajectories for mid- and post-training of LongCat's general models.

Related event: Meituan LongCat Unveils DeepResearch Multi-Agent Report System(2 posts)→

Original post →

More from coding & agent

coding & agent channel →