ChatPaper.aiChatPaper

AgentOhana:為有效的智能體學習設計統一的數據和訓練管道。

AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning

February 23, 2024
作者: Jianguo Zhang, Tian Lan, Rithesh Murthy, Zhiwei Liu, Weiran Yao, Juntao Tan, Thai Hoang, Liangwei Yang, Yihao Feng, Zuxin Liu, Tulika Awalgaonkar, Juan Carlos Niebles, Silvio Savarese, Shelby Heinecke, Huan Wang, Caiming Xiong
cs.AI

摘要

由大型語言模型(LLMs)驅動的自主代理引起了相當多的研究關注。然而,要充分發揮LLMs在基於代理的任務中的潛力,面臨著困難,原因在於多樣數據來源的異質性,其中包括多輪軌跡。在本文中,我們介紹AgentOhana作為應對這些挑戰的全面解決方案。AgentOhana匯總了來自不同環境的代理軌跡,涵蓋各種情境。它精心將這些軌跡標準化並統一成一致的格式,從而簡化了用於代理訓練的通用數據加載器的創建。通過數據統一,我們的訓練流程在不同數據來源之間保持平衡,在數據集劃分和模型訓練期間保持設備之間的獨立隨機性。此外,我們提出了xLAM-v0.1,一個針對AI代理量身定制的大型動作模型,展示了在各種基準測試中的優異表現。
English
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 AgentOhana as a comprehensive solution to address these challenges. 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 xLAM-v0.1, a large action model tailored for AI agents, which demonstrates exceptional performance across various benchmarks.
PDF163December 15, 2024