{
  "id": 10839711,
  "title": "CoEM: Empowering Long-Context Reasoning with Commit-on-Evidence Memory",
  "url": "https://urgent.news/2026/09/29/coem-empowering-long-context-reasoning-with-commit-on-evidence-memory",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-29T07:48:18.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.36935v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Long-context reasoning is essential for complex and long-horizon tasks, yet the performance of large language models (LLMs) degrades as context length increases. Recent approaches address this by processing input chunk by chunk while maintaining a bounded textual memory in model context. However, premature information compression can discard critical details essential for subsequent reasoning. In…",
  "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."
}