{
  "id": 9689991,
  "title": "PoEM: Predicting RL Outcomes from Existing Policies",
  "url": "https://urgent.news/2026/09/24/poem-predicting-rl-outcomes-from-existing-policies",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-24T17:50:25.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.30226v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Foundation models are post-trained with reinforcement learning (RL) to maximize specific rewards, such as human alignment, correctness, or instruction following. This post-training process is computationally intensive, sometimes unstable, and has to be run from scratch every time the reward model changes or when we want to combine multiple rewards. We hence ask: given a new reward function, is it…",
  "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."
}