{
  "id": 5793,
  "url": "https://arxiv.org/abs/2604.14683v1",
  "title": "DR$^{3}$-Eval: Towards Realistic and Reproducible Deep Research Evaluation",
  "summary": "Deep Research Agents (DRAs) aim to solve complex, long-horizon research tasks involving planning, retrieval, multimodal understanding, and report generation, yet their evaluation remains challenging due to dynamic web environments and ambiguous task definitions. We propose DR$^{3}$-Eval, a realistic and reproducible benchmark for evaluating deep research agents on multimodal, multi-file report generation. DR$^{3}$-Eval is constructed from authentic user-provided materials and paired with a per-t",
  "authors": "Qianqian Xie, Qingheng Xiong, He Zhu, Tiantian Xia, Xueming Han, Fanyu Meng et al.",
  "category": "research",
  "topics": "agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-04-16T06:40:02.000Z",
  "fetched_at": "2026-07-14T16:32:02.059Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5793",
  "original_url": "https://arxiv.org/abs/2604.14683v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}