Looped Flows: new denoising-based reasoning method hits SoTA on ARC-AGI-1 and ARC-AGI-2
NandoDF · x · 2026-09-13
- Thinking with Looped Flows introduces a new approach to reasoning: training recurrent reasoning with local denoising objectives, letting neural nets "think by denoising."
- It achieves SoTA among looped models on both ARC-AGI-1 and ARC-AGI-2.
- Nando de Freitas amplified the thread, calling it awesome work on reasoning with flow-based language models.
Related event: Looped Flows: Denoising-Trained Recurrent Reasoning Tops Loop-Model ARC-AGI(6 posts)→
More from Research
- Regehr's 'Piano Test': would you trust formally verified code with your life? — moyix · 2026-10-28
- NVIDIA Research releases Foundation4D: unified 4D perception model turns camera video into 3D scenes, no lidar needed — Scobleizer · 2026-10-28
- Moving Atoms Engine turns real-world spaces and cities into high-resolution 4D models for sim — Scobleizer · 2026-10-28
- Rachel Thomas points to classic paper on articulating the value of not building tech — math_rachel · 2026-10-28
- Meta's Omnilingual MT covers 1,600 languages, 1B–8B models rival 70B LLMs — kalyan_kpl · 2026-10-28
- Supercharging LLM classification with logprobs: soft classifiers you can threshold-tune — JnBrymn · 2026-10-28