@inproceedings{zhang-etal-2025-actionstudio,
    title = "{A}ction{S}tudio: A Lightweight Framework for Data and Training of Large Action Models",
    author = "Zhang, Jianguo  and
      Hoang, Thai Quoc  and
      Zhu, Ming  and
      Liu, Zuxin  and
      Wang, Shiyu  and
      Awalgaonkar, Tulika Manoj  and
      Prabhakar, Akshara  and
      Chen, Haolin  and
      Yao, Weiran  and
      Liu, Zhiwei  and
      Tan, Juntao  and
      Niebles, Juan Carlos  and
      Heinecke, Shelby  and
      Wang, Huan  and
      Savarese, Silvio  and
      Xiong, Caiming",
    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.1090/",
    pages = "21499--21513",
    ISBN = "979-8-89176-332-6",
    abstract = "Large Action models are essential for enabling autonomous agents to perform complex tasks. However, training such models remains challenging due to the diversity of agent environments and the complexity of noisy agentic data. Existing infrastructure offers limited support for scalable, agent-specific fine-tuning and standardized agent data processing. We introduce \textbf{ActionStudio}, a lightweight and extensible data and training framework designed for large action models. ActionStudio unifies diverse agent trajectories using our proposed Unified Format 2.0, supports a range of training workflows with optimized multi-node distributed setup, and integrates robust preprocessing and real-time verification tools. ActionStudio demonstrates up to 9$\times$ higher throughput compared to existing agentic training frameworks, and our trained models yield top performances across public and realistic agent benchmarks. To support the broader research community, we open-source the ActionStudio framework and release \textit{actionstudio-98k}, a curated dataset of 98k high-quality trajectories."
}