{
  "id": 12772267,
  "title": "Q-Learning with Scalar Adjoint Matching",
  "url": "https://urgent.news/2026/10/07/q-learning-with-scalar-adjoint-matching",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-07T17:13:35.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.10437v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Flow policies capture rich and diverse action distributions, and fine-tuning them with off-policy RL to improve beyond the demonstrations has drawn growing interest. However, fine-tuning a flow policy against a learned value function is not trivial, because the policy generates its action over many flow steps. Adjoint matching offers a principled way to update the flow model itself by propagating…",
  "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."
}