Looped Flows: Recurrent Denoising Reasoning Hits SoTA on ARC-AGI-1 and 2
erikjbekkers · x · 2026-09-11
- 核心思路:用局部去噪目标训练循环推理(recurrent reasoning),即让网络通过迭代去噪过程实现思考。
- 成绩:在循环推理(looped)模型类别中于 ARC-AGI-1 和 ARC-AGI-2 上均达到 SoTA。
- 这是推理架构层面的一条新路线,区别于主流 chain-of-thought 风格的自回归推理。
- 由 ayhozade 与 David Lee 等多位合作者共同完成,详细内容见原帖线程。
Related event: Thinking with Looped Flows Tops ARC-AGI for Looped Models(2 posts)→
More from Research
- Tao and Fields Medalists' two objections to AI in math, and why they're weak — RexDouglass · 2026-09-12
- Conjectures launches Bittensor bounties paying TAO for cracking math problems open 30-80 years, judged by machine — markjeffrey · 2026-09-12
- FADA (CoRL 2026) open-sourced: humanoid robots adapt to new conditions from 2 minutes of experience — GuanyaShi · 2026-09-12
- Intel's silicon photonics couplers hit 1-1.5 dB IL, with visible epoxy delamination flaws — jwt0625 · 2026-09-12
- CPO paper criticized for vague DLW-to-PIC coupling description: 'such as TCB' — jwt0625 · 2026-09-12
- Fly connectome trained to play a Flappy Bird–style game — TinfoilTricorn · 2026-09-12