{
  "id": 14385221,
  "title": "ChunkAct: Action Chunking for Agentic Robotics",
  "url": "https://urgent.news/2026/10/13/chunkact-action-chunking-for-agentic-robotics",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-13T17:59:57.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2610.18874v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Agentic robotics places a large language model (LLM) agent in the robot control loop, where it composes perception, motion, and vision-language-action (VLA) tools under the guidance of a memory and thereby generalizes to new tasks without retraining. This generality comes at a steep price in efficiency. Every primitive requires a round of LLM reasoning over the full interaction history, so the…",
  "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."
}