Xiaohongshu Open Sources dots3-notePreview, Proposes TEMPO Training Paradigm
小红书技术REDtech · wechat · 2026-08-14
Xiaohongshu open-sourced dots3-notePreview, the lightest model in the dots3 series (280B total params, 16B active). It supports 512K context and multimodal understanding, optimized for complex reasoning and long-horizon Agent tasks. The team proposed TEMPO, a training paradigm using test-time scaled value estimation and macro-step policy optimization to solve credit assignment in long-horizon RL. The model achieved a perfect gold medal score in internal IMO 2026 testing. Two evaluation environments, VibeSearchBench and VibeLifeBench, were also released.
Related event: Xiaohongshu Open-Sources dots3-note 280B Multimodal Model(14 posts)→
More from Models
- From botching 9.9 vs 9.11 to tackling the hardest math problems in two years — Yuchenj_UW · 2026-10-07
- OpenAI claims 372 unsolved problems cracked, averaging about 3 hours each — i_dg23 · 2026-10-07
- Benchmark: OpenAI Decisions API costs 2x more, 5-10% worse than Jev — xeophon · 2026-10-07
- Cagliostro V3.5 135M Dethrones SmolLM2-135M on Open SLM Leaderboard at 27.49 — Megneous · 2026-10-07
- "If you still think LLMs suck at math, it's a skill issue" — hot take gains traction — alejandroll10 · 2026-10-07
- Sauers_: Opus 5.5 shows fewer strong technical opinions than Fable 5.1 and 5 — Sauers_ · 2026-10-07