{
  "id": 11916,
  "url": "https://arxiv.org/abs/2607.16900",
  "title": "Environment-free Synthetic Data Generation for API-Calling Agents",
  "summary": "Training API-calling large language model (LLM) agents demands massive amounts of high-quality trajectories. However, collecting such data at scale typically requires fully implemented environments with executable APIs and realistic, pre-populated backend databases, creating a major bottleneck for scalability. To overcome this, we propose an environment-free synthetic data generation approach that leverages LLMs as on-the-fly digital world models. Given only API specifications, our method genera",
  "authors": "Seanie Lee, Sanjoy Chowdhury, Chao Jiang, Cheng-Yu Hsieh, Ting-Yao Hu, Alexander T Toshev",
  "category": "research",
  "topics": "agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-17T20:00:00.000Z",
  "fetched_at": "2026-07-21T05:10:12.656Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/11916",
  "original_url": "https://arxiv.org/abs/2607.16900",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}