Youtu-Agent自动化生成与优化智能体，降低配置成本并提升动态适应能力。
Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization
- 模块化框架支持自动合成工具、提示和配置，分工作流与元智能体两种模式。
- 在WebWalkerQA和GAIA上分别达71.47%和72.8%准确率，实践模块提升竞赛表现2.7%-5.4%。
- 结合上下文优化与强化学习，实现无参数更新的持续进化，适合需要长期演化的场景。
现有大语言模型智能体框架面临配置成本高和能力静态两大挑战。构建高质量智能体需大量手动工具集成与提示工程，而部署后难以适应动态环境。为此，我们提出Youtu-Agent，一个用于自动化生成与持续演进大模型智能体的模块化框架。该框架通过解耦执行环境、工具集与上下文管理，实现灵活复用与自动合成。引入两种生成范式：工作流模式适用于标准任务，元智能体模式可自动生成工具代码、提示与配置以应对复杂非标需求。此外，构建混合策略优化系统：（1）智能体实践模块通过上下文优化积累经验，无需参数更新即可提升性能；（2）智能体强化学习模块结合分布式训练框架，实现端到端大规模稳定强化学习。实验表明，基于开源权重模型，Youtu-Agent在WebWalkerQA（71.47%）与GAIA（72.8%）上达到领先水平。自动化生成管道工具合成成功率超81%，实践模块使AIME 2024/2025表现分别提升+2.7%与+5.4%。智能体强化学习训练在7B模型上提速40%，编码/推理与搜索能力分别提升最高35%与21%于Maths及通用/多跳问答基准。
原文摘要 · Abstract (English)
Existing Large Language Model (LLM) agent frameworks face two significant challenges: high configuration costs and static capabilities. Building a high-quality agent often requires extensive manual effort in tool integration and prompt engineering, while deployed agents struggle to adapt to dynamic environments without expensive fine-tuning. To address these issues, we propose \textbf{Youtu-Agent}, a modular framework designed for the automated generation and continuous evolution of LLM agents. Youtu-Agent features a structured configuration system that decouples execution environments, toolkits, and context management, enabling flexible reuse and automated synthesis. We introduce two generation paradigms: a \textbf{Workflow} mode for standard tasks and a \textbf{Meta-Agent} mode for complex, non-standard requirements, capable of automatically generating tool code, prompts, and configurations. Furthermore, Youtu-Agent establishes a hybrid policy optimization system: (1) an \textbf{Agent Practice} module that enables agents to accumulate experience and improve performance through in-context optimization without parameter updates; and (2) an \textbf{Agent RL} module that integrates with distributed training frameworks to enable scalable and stable reinforcement learning of any Youtu-Agents in an end-to-end, large-scale manner. Experiments demonstrate that Youtu-Agent achieves state-of-the-art performance on WebWalkerQA (71.47\%) and GAIA (72.8\%) using open-weight models. Our automated generation pipeline achieves over 81\% tool synthesis success rate, while the Practice module improves performance on AIME 2024/2025 by +2.7\% and +5.4\% respectively. Moreover, our Agent RL training achieves 40\% speedup with steady performance improvement on 7B LLMs, enhancing coding/reasoning and searching capabilities respectively up to 35\% and 21\% on Maths and general/multi-hop QA benchmarks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。