{
  "id": 5157,
  "url": "https://arxiv.org/abs/2604.27977v2",
  "title": "D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery",
  "summary": "Despite recent progress in language models and agents for scientific data-driven discovery, further advancing their capabilities is held back by the absence of verifiable environments representing real-world scientific tasks. To fill this gap, we introduce D3-Gym, the first automatically constructed dataset with verifiable environments for scientific Data-Driven Discovery. D3-Gym comprises (1) 565 tasks sourced from 239 real scientific repositories across four disciplines where (2) each task is ",
  "authors": "Hanane Nour Moussa, Yifei Li, Zhuoyang Li, Yankai Yang, Cheng Tang, Tianshu Zhang et al.",
  "category": "research",
  "topics": "agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-30T15:06:56.000Z",
  "fetched_at": "2026-07-14T16:31:31.213Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5157",
  "original_url": "https://arxiv.org/abs/2604.27977v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}