ActionStudio: A Lightweight Framework for Data and Training of Large Action Models
This work addresses the problem of scalable and efficient training for autonomous agents, providing a practical tool for researchers and developers, though it is incremental as it builds on existing infrastructure.
The paper tackles the challenge of training large action models for autonomous agents by introducing ActionStudio, a lightweight framework that unifies agent trajectories and optimizes training workflows, achieving up to 9x higher throughput and top performance on benchmarks.
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 9x 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 actionstudio-98k, a curated dataset of 98k high-quality trajectories. Code: https://github.com/SalesforceAIResearch/xLAM.