{
  "id": 12657,
  "url": "https://arxiv.org/abs/2607.18603",
  "title": "AutoIndex: Learning Representation Programs for Retrieval",
  "summary": "We present AutoIndex, a framework for learning representation programs: executable transformations that map raw documents into the representations exposed to a retrieval system. Rather than tuning retrievers, rerankers, or a small set of preprocessing hyperparameters, AutoIndex searches over programs that slice, enrich, normalize, reweight, or reorganize documents before indexing. At each iteration, AutoIndex performs validation-guided program search, in which agents diagnose failures of the cur",
  "authors": "Sam O'Nuallain, Nithya Rajkumar, Ramya Narayanasamy, Hanna Jiang, Shreyas Chaudhari, Andrew Drozdov",
  "category": "research",
  "topics": "healthcare,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-20T20:00:00.000Z",
  "fetched_at": "2026-07-23T05:10:49.458Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/12657",
  "original_url": "https://arxiv.org/abs/2607.18603",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}