# Deep Research

2 related articles

Subscribe to updates

Preferred Networks Oct 27, 2026
PFN's PLaMo 3.1 Prime puts reasoning and fast answers in one model, so serving no longer needs double the compute
PFN has released PLaMo 3.1 Prime, a domestically developed foundation model that folds reasoning and non-reasoning modes into one model and adds web search plus a Deep Research feature. PLaMo 3.0 Prime trained and served the two modes separately; under the configuration reported at the time, offering both took twice the compute of serving one single-mode model (PLaMo 2.2 Prime or PLaMo 3.0 Prime Beta). The new model is instruction-tuned in two stages, the second mixing in examples with the reasoning traces removed so one model switches per request. Against PLaMo 3.0 Prime it averages 2.4 points higher on reasoning-mode web-search QA and 11.1 points higher on search reports.
PFN has released PLaMo 3.1 Prime, a domestically developed foundation model that folds reasoning and non-reasoning modes into one model and adds web search plus a Deep Research feature. PLaMo 3.0 Prime trained and served the two modes separately; under the configuration reported at the time, offering both took twice the compute of serving one single-mode model (PLaMo 2.2 Prime or PLaMo 3.0 Prime Beta). The new model is instruction-tuned in two stages, the second mixing in examples with the reasoning traces removed so one model switches per request. Against PLaMo 3.0 Prime it averages 2.4 points higher on reasoning-mode web-search QA and 11.1 points higher on search reports.
PLaMo 3.1 Prime Hybrid reasoning model Deep Research Speculative Decoding KV Cache
arXiv Sep 30, 2026
Meituan's LongCat team splits deep research into planning, parallel section research, and global-to-local editing via ResearchSpec, scoring 55.25, 51.35, and 79.83 on three public benchmarks
Meituan's LongCat team presents LongCat-DeepResearch, which shifts early research iteration from the full report to an executable ResearchSpec: multiple planning agents first search external sources and consolidate a research plan, researchers then investigate and draft citation-bearing sections in parallel independent contexts, and a Global Editor assigns cross-section ownership while Local Editors make targeted revisions, yielding 55.25 on DeepResearchBench, 51.35 on DeepResearchBench II, and 79.83 on ResearchRubrics, and 76.04 on an in-house benchmark, second among four compared systems.
Meituan's LongCat team presents LongCat-DeepResearch, which shifts early research iteration from the full report to an executable ResearchSpec: multiple planning agents first search external sources and consolidate a research plan, researchers then investigate and draft citation-bearing sections in parallel independent contexts, and a Global Editor assigns cross-section ownership while Local Editors make targeted revisions, yielding 55.25 on DeepResearchBench, 51.35 on DeepResearchBench II, and 79.83 on ResearchRubrics, and 76.04 on an in-house benchmark, second among four compared systems.
Meituan LongCat Team（First author）
LongCat-DeepResearch ResearchSpec Multi-Agent Workflow Deep Research

You’re all caught up

PFN's PLaMo 3.1 Prime puts reasoning and fast answers in one model, so serving no longer needs double the compute

Meituan's LongCat team splits deep research into planning, parallel section research, and global-to-local editing via ResearchSpec, scoring 55.25, 51.35, and 79.83 on three public benchmarks