Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization
Yuchen Shi, Yuzheng Cai, Siqi Cai, Zihan Xu, Lichao Chen, Yulei Qin, Zhijian Zhou, Xiang Fei, Chaofan Qiu, Xiaoyu Tan, Gang Li, Zongyi Li, Haojia Lin, Guocan Cai, Yong Mao, Yunsheng Wu, Ke Li, Xing Sun

TL;DR
Youtu-Agent is a modular framework that automates the creation and continuous improvement of LLM agents through structured configuration, hybrid policy optimization, and scalable training, achieving state-of-the-art results.
Contribution
The paper introduces Youtu-Agent, a novel modular framework that automates agent generation and hybrid policy optimization, reducing manual effort and enabling scalable, adaptive LLM agents.
Findings
Achieves state-of-the-art performance on WebWalkerQA and GAIA datasets.
Over 81% success rate in automated tool synthesis.
Improves agent performance on benchmarks by up to 5.4%.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMachine Learning and Data Classification · Machine Learning in Materials Science · Topic Modeling
