{
  "id": 7486878,
  "title": "The Router Within: Eliciting Native Skill Routing from a Frozen LLM",
  "url": "https://urgent.news/2026/09/14/the-router-within-eliciting-native-skill-routing-from-a-frozen-llm",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-14T17:58:27.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.15982v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Skills extend an LLM agent beyond its parametric knowledge, and the gain they promise rests on picking the right one. Deployed harnesses route by preloading every skill's metadata into the context, which disperses the agent's attention and caps the library size. Retrieval pipelines move the selection out of the context, but also out of the agent's capability. We show that the frozen agent LLM…",
  "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."
}