{
  "id": 12292311,
  "title": "Off-Policy Merging Beats On-Policy Self-Distillation for Continual Learning",
  "url": "https://urgent.news/2026/10/05/off-policy-merging-beats-on-policy-self-distillation-for-continual",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-05T06:40:34.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.05872v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "A long-standing goal of AI is a model that can continually learn and improve itself. On post-trained models, supervised finetuning (SFT) on new data often causes poor generalization and catastrophic forgetting. As such, the conventional wisdom is that on-policy training is a prerequisite for continual learning. In practice, however, data containing new knowledge or capabilities are often…",
  "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."
}