{
  "id": 7502,
  "url": "https://arxiv.org/abs/2603.08269v1",
  "title": "SAIL: Test-Time Scaling for In-Context Imitation Learning with VLM",
  "summary": "In-context imitation learning allows robots to acquire skills from demonstrations, yet one-shot trajectory generation remains fragile under environmental variation. We propose SAIL, a framework that reframes robot imitation as an iterative refinement problem capable of scaling with test-time compute. SAIL utilizes Monte Carlo Tree Search, where each node is a complete trajectory and edges correspond to trajectory refinements. The process is guided by three core components: an automated archive o",
  "authors": "Makoto Sato, Yusuke Iwasawa, Yujin Tang, So Kuroki",
  "category": "research",
  "topics": "agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-03-09T11:39:40.000Z",
  "fetched_at": "2026-07-14T16:33:16.668Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/7502",
  "original_url": "https://arxiv.org/abs/2603.08269v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}