{
  "id": 14385223,
  "title": "Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards",
  "url": "https://urgent.news/2026/10/13/tev-scaling-long-horizon-agentic-environments-with-dense-progress",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-13T17:59:51.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.18868v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Long-horizon agents have drawn growing attention for their ability to work autonomously -- from hours to days -- on economically valuable tasks, a capability essential to automated discovery and recursive self-improvement (RSI). Yet open-source models still struggle on long-horizon tasks, largely for lack of both training data and a working recipe, and scaling both is hard: long, complex tasks…",
  "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."
}