{
  "id": 6702094,
  "title": "Thinking with Looped Flows",
  "url": "https://urgent.news/2026/09/10/thinking-with-looped-flows",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-10T16:52:54.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.11801v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Humans and machines often solve harder problems by spending more time on computation. In deep learning, looped models implement this idea during inference by recurrently updating a hidden state. In practice, however, their training backpropagates through only one or a few updates, making it hard to train early updates to support future ones. We propose looped flows, an approach that sidesteps…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}