xLAM：赋能AI智能体系统的大型行动模型家族
xLAM: A Family of Large Action Models to Empower AI Agent Systems
AI总结：
本文发布xLAM大型行动模型家族，包含五种1B至8x22B参数的稠密与混合专家架构模型，通过统一增强的数据流水线训练，在Berkeley Function-Calling Leaderboard上超越GPT-4等模型，旨在提升开源LLMs的智能体任务性能。
摘要：
由大型语言模型（LLMs）驱动的自主智能体已引起广泛的研究关注。然而，开源社区在开发面向智能体任务的专用模型时面临诸多挑战，主要原因是高质量智能体数据集的稀缺以及该领域缺乏标准协议。我们推出并公开发布了xLAM，这是一个专为AI智能体任务设计的大型行动模型系列。xLAM系列包含五个模型，采用稠密架构和混合专家架构，参数规模从1B到8x22B不等，通过一个可扩展、灵活的流水线进行训练，该流水线统一、增强并合成了多样化的数据集，以提升AI智能体在不同环境中的泛化能力和性能。我们的实验结果表明，xLAM在多个智能体能力基准测试中持续展现出卓越的性能，尤其是在Berkeley Function-Calling Leaderboard上取得了第1名，在工具使用方面超越了GPT-4、Claude-3以及许多其他模型。通过发布xLAM系列，我们旨在提升开源LLMs在自主AI智能体方面的性能，有望加速进展并推动高性能智能体任务模型的普及化。模型可在 https://huggingface.co/collections/Salesforce/xlam-models-65f00e2a0a63bbcd1c2dade4 获取。
英文摘要：
Autonomous agents powered by large language models (LLMs) have attracted significant research interest. However, the open-source community faces many challenges in developing specialized models for agent tasks, driven by the scarcity of high-quality agent datasets and the absence of standard protocols in this area. We introduce and publicly release xLAM, a series of large action models designed for AI agent tasks. The xLAM series includes five models with both dense and mixture-of-expert architectures, ranging from 1B to 8x22B parameters, trained using a scalable, flexible pipeline that unifies, augments, and synthesizes diverse datasets to enhance AI agents' generalizability and performance across varied environments. Our experimental results demonstrate that xLAM consistently delivers exceptional performance across multiple agent ability benchmarks, notably securing the 1st position on the Berkeley Function-Calling Leaderboard, outperforming GPT-4, Claude-3, and many other models in terms of tool use. By releasing the xLAM series, we aim to advance the performance of open-source LLMs for autonomous AI agents, potentially accelerating progress and democratizing access to high-performance models for agent tasks. Models are available at https://huggingface.co/collections/Salesforce/xlam-models-65f00e2a0a63bbcd1c2dade4
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
