{
  "id": 14385240,
  "title": "Pack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents",
  "url": "https://urgent.news/2026/10/13/pack-light-carryon-building-object-oriented-context-for-long-horizon",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-13T17:35:27.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.18784v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Long-horizon agents accumulate progress in persistent task state, yet repeatedly process interaction histories describing how that progress was achieved. This raises a natural question: can long-horizon context instead be organized around reusable progress rather than the history that produced it? In this paper, we introduce CarryOn, an object-oriented context runtime that organizes continuation…",
  "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."
}