Language agents have achieved considerable performance on various complex question-answering tasks. Despite the incessant exploration in this field, existing language agent systems still struggle with costly, non-reproducible data reliance and face the challenge of compelling a single model for multiple functions. To this end, we introduce AutoAct, an automatic agent learning framework that does not rely on large-scale annotated data and synthetic trajectories from closed-source models (e.g., GPT-4). Given limited data with a tool library, AutoAct first automatically synthesizes planning trajectories without any assistance from humans or strong closed-source models. Then, AutoAct leverages a division-of-labor strategy to automatically differentiate based on the target task information and synthesized trajectories, producing a sub-agent group to complete the task. We conduct comprehensive experiments with different LLMs, which demonstrates that AutoAct yields better or parallel performance compared to various strong baselines. Further analysis demonstrates the effectiveness of the division-of-labor strategy, with the trajectory quality generated by AutoAct significantly outperforming that of others. Code will be available at https://github.com/zjunlp/AutoAct.

翻译：语言智能体在各类复杂问答任务中已取得显著性能。尽管该领域探索不断深入，现有语言智能体系统仍面临成本高昂、不可复现的数据依赖问题，以及迫使单一模型承担多重功能的挑战。为此，我们提出AutoAct——一种无需依赖大规模标注数据和闭源模型（如GPT-4）合成轨迹的自动智能体学习框架。在有限数据和工具库条件下，AutoAct首先自动合成规划轨迹，无需人工或强闭源模型辅助。随后，AutoAct基于目标任务信息与合成轨迹，采用分工策略自动进行差异化划分，生成子智能体群组以完成任务。我们在不同大语言模型上开展全面实验，结果表明AutoAct相较于各类强基线模型取得更优或相当的性能。进一步分析验证了分工策略的有效性，AutoAct生成的轨迹质量显著超越其他方法。代码将开源至https://github.com/zjunlp/AutoAct。