Action models are essential for enabling autonomous agents to perform complex tasks. However, training large action models remains challenging due to the diversity of agent environments and the complexity of agentic data. Despite growing interest, existing infrastructure provides limited support for scalable, agent-specific fine-tuning. We present ActionStudio, a lightweight and extensible data and training framework designed for large action models. ActionStudio unifies heterogeneous agent trajectories through a standardized format, supports diverse training paradigms including LoRA, full fine-tuning, and distributed setups, and integrates robust preprocessing and verification tools. We validate its effectiveness across both public and realistic industry benchmarks, demonstrating strong performance and practical scalability. We open-sourced code and data atthis https URLto facilitate research in the community.
View on arXiv@article{zhang2025_2503.22673,
title={ ActionStudio: A Lightweight Framework for Data and Training of Large Action Models },
author={ Jianguo Zhang and Thai Hoang and Ming Zhu and Zuxin Liu and Shiyu Wang and Tulika Awalgaonkar and Akshara Prabhakar and Haolin Chen and Weiran Yao and Zhiwei Liu and Juntao Tan and Juan Carlos Niebles and Shelby Heinecke and Huan Wang and Silvio Savarese and Caiming Xiong },
journal={arXiv preprint arXiv:2503.22673},
year={ 2025 }
}