{
  "id": 6092,
  "url": "https://arxiv.org/abs/2604.09741v1",
  "title": "ExecTune: Effective Steering of Black-Box LLMs with Guide Models",
  "summary": "For large language models deployed through black-box APIs, recurring inference costs often exceed one-time training costs. This motivates composed agentic systems that amortize expensive reasoning into reusable intermediate representations. We study a broad class of such systems, termed Guide-Core Policies (GCoP), in which a guide model generates a structured strategy that is executed by a black-box core model. This abstraction subsumes base, supervised, and advisor-style approaches, which diffe",
  "authors": "Vijay Lingam, Aditya Golatkar, Anwesan Pal, Ben Vo, Narayanan Sadagopan, Alessandro Achille et al.",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-09T23:27:46.000Z",
  "fetched_at": "2026-07-14T16:32:15.635Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6092",
  "original_url": "https://arxiv.org/abs/2604.09741v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}