{
  "id": 3551,
  "url": "https://arxiv.org/abs/2605.29218v1",
  "title": "GTA: Generating Long-Horizon Tasks for Web Agents at Scale",
  "summary": "Web agents, which couple language models with browsing and tool-use capabilities, show promise as open web assistants. Yet progress is increasingly limited by the lack of scalable, process-level supervision. Existing benchmarks are largely manually constructed, providing only coarse start-goal annotations without intermediate trajectories, while recent automatic generation efforts remain expensive, biased, and shallow. These limitations prevent reliable training and evaluation of agents that mus",
  "authors": "Tenghao Huang, Kung-Hsiang Huang, Prafulla Kumar Choubey, Yilun Zhou, Muhao Chen, Jonathan May et al.",
  "category": "research",
  "topics": "bias-fairness,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-28T01:05:50.000Z",
  "fetched_at": "2026-07-14T16:30:18.857Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3551",
  "original_url": "https://arxiv.org/abs/2605.29218v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}