Open-Sourcing dots3-note: 280B Multimodal Model & TEMPO RL Framework for Long-Horizon Agents
teortaxesTex · x · 2026-08-14
The team has released dots3-note Preview, an open-source 280B parameter (16B active) multimodal model designed for complex reasoning and long-horizon agents.
Alongside the model, they introduced TEMPO (Test-time-scaled Value Estimation with Macro-step Policy Optimization), a novel RL framework. TEMPO addresses the challenge of training agents when a single rollout takes tens of hours by converting intermediate self-critiquing into learning signals before the task is fully complete.
They have also open-sourced two new benchmarks: VibeSearchBench and VibeLifeBench.
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