{
  "id": 9068366,
  "title": "ARM: Attention with Routed-Memory for Learnable Sparse Control",
  "url": "https://urgent.news/2026/09/21/arm-attention-with-routed-memory-for-learnable-sparse-control",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-21T11:11:17.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.24417v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Despite advances in long-context inference, large language models (LLMs) remain fundamentally limited by the key-value (KV) caching mechanisms that are necessary for stable computation. Techniques such as selective token eviction and pruning have vastly mitigated these issues, but often discard core information to manage the growing cache. In this paper, we propose Attention with Routed Memory…",
  "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."
}