| name | youtu-agent-framework |
| title | Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy Optimization |
| version | 0.0.2 |
| engine | skillxiv-v0.0.2-claude-opus-4.6 |
| license | MIT |
| url | https://arxiv.org/abs/2512.24615 |
| keywords | ["Agent Framework","Automated Agent Generation","LLM Agents","Policy Optimization","Agent RL"] |
| description | Build scalable LLM agent frameworks with automated generation of tools, prompts, and configurations, plus continuous optimization through experience accumulation and reinforcement learning—achieving 71.47% on WebWalkerQA and 72.8% on GAIA. |
Overview
Youtu-Agent is a modular framework for constructing and continuously improving LLM-based agents. It addresses two critical bottlenecks: the high manual effort required for agent configuration (tool integration, prompt engineering) and the difficulty in adapting deployed agents without expensive fine-tuning.
Key Innovation: Automated generation of complete agent configurations from high-level task descriptions, combined with two optimization mechanisms: Agent Practice (low-cost in-context learning) and Agent RL (end-to-end reinforcement learning at scale).
Core Architecture
The framework organizes agent execution into three hierarchical layers:
Environment Layer
Provides foundational execution context and primitives. Typical backends include browser automation (Playwright), OS shells, and sandboxed code execution (E2B).
Tools Layer
Encapsulates atomic and composite operations: (1) environment-related tools wrapping low-level APIs, (2) environment-independent utilities, (3) MCP tools for external services.
Agent Layer
Houses the LLM-driven planner with a perceive-reason-act loop and Context Manager for managing long-horizon interactions.
Automated Generation Mechanisms
Workflow Mode
A deterministic four-stage pipeline for routine tasks:
- Intent Clarification and Decomposition - Analyze and structure task requirements
- Tool Retrieval and Ad-hoc Synthesis - Search existing toolkit library; auto-generate missing tools
- Prompt Engineering - Generate optimized system instructions
- Configuration Assembly - Compile all components into YAML configuration
This mode achieves 100% configuration validity on the 80-task AgentGen benchmark.
Meta-Agent Mode
For complex or ambiguous requirements, deploy an Architect Agent with tools: search_tool, create_tool, ask_user, and create_agent_config. The meta-agent dynamically plans generation through multi-turn clarification and tool synthesis.
Example: Given "Summarize today's trending papers on multi-agent systems and download PDFs," the meta-agent:
- Calls
search_tool to find existing arxiv toolkit
- Calls
create_tool to synthesize fetch_daily_papers tool
- Calls
create_agent_config to assemble final configuration
Tool synthesis implementation:
