{
  "id": 152,
  "url": "https://arxiv.org/abs/2607.06413v1",
  "title": "An Experimental Design Approach to Evaluating Agentic AI's Autonomous Model Discovery",
  "summary": "Large language model coding agents increasingly perform open-ended data modeling and analysis. These agents are stochastic and adaptive, and therefore their autonomous model discovery behavior cannot be adequately characterized by a single benchmark run. In this work, we propose an experimental design and analysis framework for systematically evaluating this discovery process, quantifying its variability, and identifying important factors. The proposed framework treats these agents as stochastic",
  "authors": "Hao He, Xueying Liu, Chris J. Kuhlman, Xinwei Deng",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-07T15:43:22.000Z",
  "fetched_at": "2026-07-14T14:14:19.969Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/152",
  "original_url": "https://arxiv.org/abs/2607.06413v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}