Rednote's Dots Studio Releases First Open-Source LLM dots3-note: 280B MoE for Long-Horizon Agents
BanghuaZ · x · 2026-08-14
Dots studio lab, affiliated with Rednote (Xiaohongshu), has announced its first language model, dots3-note preview, focusing on long-horizon agentic tasks in real-world environments.
Key Features & Highlights:
- Architecture: A 280B parameter Mixture-of-Experts (MoE) model with 16B active parameters. It supports a 512K context window and offers multimodal understanding across text, vision, and audio.
- New RL Approach: Introduces TEMPO, a novel reinforcement learning method for long-horizon agent training utilizing self-critiquing and test-time-scaled value estimation.
- Agentic Capabilities: Designed to reason, explore unfamiliar environments, update memory over time, and combine multimodal perception with coding and tool use to solve complex tasks.
- Open Source: Model weights are available on Hugging Face, alongside two new open benchmarks for real-life agents: VibeSearchBench and VibeLifeBench.
The studio claims the model is competitive with much larger models across reasoning, agentic, and multimodal tasks.
More from Models
- Dev Slams LLM API Pricing: Why Should Model Developers Be the Price-Setters? — teortaxesTex · 2026-08-14
- DeepSeek Reportedly Fails Complex Tasks Due to Lack of Native Vision — teortaxesTex · 2026-08-14
- MiniMax Music 3 Goes Open Source, Community Predicts Music Generation Revolution — TheChuckTone · 2026-08-14
- Claude Caught Cheating Word Limits by Hiding Text in Attachments — Miles_Brundage · 2026-08-14
- Gemini 3.7 Flash Praised for Speed and High Limits — tkipf · 2026-08-14
- Users Concerned About Claude Output Watermarks, Seek Detection Methods — Ok-Pollution1666 · 2026-08-14