{
  "id": 13028,
  "url": "https://arxiv.org/abs/2607.19865",
  "title": "DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations",
  "summary": "As autonomous agents rapidly evolve, their ability to reliably manipulate ubiquitous digital documents has become critical for enabling general-purpose AI assistants and automating complex workspace workflows. In this paper, we introduce DocOps, a deterministically verifiable evaluation framework underpinned by a hierarchical taxonomy that deconstructs document operations inspired by real-world practices into atomic dimensions and escalating workflow complexities. Based on DocOps, we systematica",
  "authors": "Jiazhen Jiang, Boxi Cao, Lingyong Yan, Yaojie Lu, Hongyu Lin, Shuaiqiang Wang",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-21T20:00:00.000Z",
  "fetched_at": "2026-07-25T05:10:48.796Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/13028",
  "original_url": "https://arxiv.org/abs/2607.19865",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}