@inproceedings{sullivan-etal-2025-procedural,
    title = "Procedural Environment Generation for Tool-Use Agents",
    author = "Sullivan, Michael  and
      Hartmann, Mareike  and
      Koller, Alexander",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.936/",
    pages = "18555--18573",
    ISBN = "979-8-89176-332-6",
    abstract = "Although the power of LLM tool-use agents has ignited a flurry of recent research in this area, the curation of tool-use training data remains an open problem$\textemdash$especially for online RL training. Existing approaches to synthetic tool-use data generation tend to be non-interactive and/or non-compositional. We introduce RandomWorld, a pipeline for the procedural generation of interactive tools and compositional tool-use data. We show that models tuned via SFT and RL on synthetic RandomWorld data improve on a range of tool-use benchmarks, and set the new SoTA for two metrics on the NESTFUL dataset. Further experiments show that downstream performance scales with the amount of RandomWorld-generated training data, opening up the possibility of further improvement through the use of entirely synthetic data."
}