Autonomous agents powered by large language models (LLMs) have garnered significant research attention. However, fully harnessing the potential of LLMs for agent-based tasks presents inherent challenges due to the heterogeneous nature of diverse data sources featuring multi-turn trajectories. In this paper, we introduce \textbf{AgentOhana} as a comprehensive solution to address these challenges. \textit{AgentOhana} aggregates agent trajectories from distinct environments, spanning a wide array of scenarios. It meticulously standardizes and unifies these trajectories into a consistent format, streamlining the creation of a generic data loader optimized for agent training. Leveraging the data unification, our training pipeline maintains equilibrium across different data sources and preserves independent randomness across devices during dataset partitioning and model training. Additionally, we present \textbf{xLAM-v0.1}, a large action model tailored for AI agents, which demonstrates exceptional performance across various benchmarks. Begin the exploration at \url{https://github.com/SalesforceAIResearch/xLAM}.
@article{arxiv.2402.15506,
title = {AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning},
author = {Jianguo Zhang and Tian Lan and Rithesh Murthy and Zhiwei Liu and Weiran Yao and Ming Zhu and Juntao Tan and Thai Hoang and Zuxin Liu and Liangwei Yang and Yihao Feng and Shirley Kokane and Tulika Awalgaonkar and Juan Carlos Niebles and Silvio Savarese and Shelby Heinecke and Huan Wang and Caiming Xiong},
journal= {arXiv preprint arXiv:2402.15506},
year = {2024}
}
Comments
Add GitHub repo link at \url{https://github.com/SalesforceAIResearch/xLAM} and HuggingFace model link at \url{https://huggingface.co/Salesforce/xLAM-v0.1-r}