ActionStudio: A Lightweight Framework for Data and Training of Large Action Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912487137345536 |
|---|---|
| author | Zhang, Jianguo Hoang, Thai Zhu, Ming Liu, Zuxin Wang, Shiyu Awalgaonkar, Tulika Prabhakar, Akshara Chen, Haolin Yao, Weiran Liu, Zhiwei Tan, Juntao Niebles, Juan Carlos Heinecke, Shelby Wang, Huan Savarese, Silvio Xiong, Caiming |
| author_facet | Zhang, Jianguo Hoang, Thai Zhu, Ming Liu, Zuxin Wang, Shiyu Awalgaonkar, Tulika Prabhakar, Akshara Chen, Haolin Yao, Weiran Liu, Zhiwei Tan, Juntao Niebles, Juan Carlos Heinecke, Shelby Wang, Huan Savarese, Silvio Xiong, Caiming |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_22673 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ActionStudio: A Lightweight Framework for Data and Training of Large Action Models Zhang, Jianguo Hoang, Thai Zhu, Ming Liu, Zuxin Wang, Shiyu Awalgaonkar, Tulika Prabhakar, Akshara Chen, Haolin Yao, Weiran Liu, Zhiwei Tan, Juntao Niebles, Juan Carlos Heinecke, Shelby Wang, Huan Savarese, Silvio Xiong, Caiming Artificial Intelligence Computation and Language 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. |
| title | ActionStudio: A Lightweight Framework for Data and Training of Large Action Models |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2503.22673 |