ActionStudio: An Open-Source Lightweight Framework for Agentic Data and Training of Large Action Models

ACL ARR 2025 May Submission6651 Authors

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 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.\footnote{\url{https://anonymous.4open.science/r/actionstudio-28AB}}

Paper Type: Long

Research Area: Dialogue and Interactive Systems

Research Area Keywords: AI Agents, Agent Models, Training framework, Large Action Model

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources

Languages Studied: English

Submission Number: 6651