ActionStudio: A Lightweight Framework for Data and Training of Large Action Models
Jianguo Zhang, Thai Hoang, Ming Zhu, Zuxin Liu, Shiyu Wang, Tulika Awalgaonkar, Akshara Prabhakar, Haolin Chen, Weiran Yao, Zhiwei Liu, Juntao Tan, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong
2025-04-01
Summary
This paper introduces a new, simple way to train AI models that control actions in different environments.
What's the problem?
Training AI models to perform actions is hard because the data is complicated and environments vary a lot.
What's the solution?
The researchers created ActionStudio, a tool that makes it easier to organize data, train models, and check their performance.
Why it matters?
This work matters because it can help researchers develop better AI agents that can perform complex tasks in various situations.
Abstract
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 at https://github.com/SalesforceAIResearch/xLAM to facilitate research in the community.