忆录技能：让智能体设计智能体
Memento-Skills: Let Agents Design Agents
March 19, 2026
作者: Huichi Zhou, Siyuan Guo, Anjie Liu, Zhongwei Yu, Ziqin Gong, Bowen Zhao, Zhixun Chen, Menglong Zhang, Yihang Chen, Jinsong Li, Runyu Yang, Qiangbin Liu, Xinlei Yu, Jianmin Zhou, Na Wang, Chunyang Sun, Jun Wang
cs.AI
摘要
我们推出Memento-Skills——一种通用且可持续学习的大语言模型智能体系统，其本质是能够自主设计智能体的元智能体：该系统通过经验积累自主构建、调整并优化面向特定任务的智能体。该体系建立在基于记忆的强化学习框架之上，采用状态化提示技术，其中可复用技能（以结构化Markdown文件形式存储）作为持续演化的持久化记忆载体。这些技能同时编码了行为模式与上下文信息，使智能体能够在交互过程中持续传承知识。
系统从基础技能（如网络搜索与终端操作）起步，通过Memento²~wang2025memento2~提出的读写反射学习机制持续进化。在读阶段，支持行为训练的技能路由器根据当前状态化提示选择最相关技能；在写阶段，智能体基于新经验更新并扩展其技能库。这种闭环设计实现了无需更新大语言模型参数的持续学习，所有适应过程均通过外部化技能与提示的演化来实现。
与依赖人工设计智能体的传统方法不同，Memento-Skills使通用智能体能够端到端地为新任务自主设计智能体。通过迭代式的技能生成与优化，系统持续提升自身能力。在通用AI助手基准测试与"人类终极考试"上的实验表明，该系统分别实现了26.2%和116.2%的相对准确率提升。代码已开源：https://github.com/Memento-Teams/Memento-Skills。
English
We introduce Memento-Skills, a generalist, continually-learnable LLM agent system that functions as an agent-designing agent: it autonomously constructs, adapts, and improves task-specific agents through experience. The system is built on a memory-based reinforcement learning framework with stateful prompts, where reusable skills (stored as structured markdown files) serve as persistent, evolving memory. These skills encode both behaviour and context, enabling the agent to carry forward knowledge across interactions.
Starting from simple elementary skills (like Web search and terminal operations), the agent continually improves via the Read--Write Reflective Learning mechanism introduced in Memento~2~wang2025memento2. In the read phase, a behaviour-trainable skill router selects the most relevant skill conditioned on the current stateful prompt; in the write phase, the agent updates and expands its skill library based on new experience. This closed-loop design enables continual learning without updating LLM parameters, as all adaptation is realised through the evolution of externalised skills and prompts.
Unlike prior approaches that rely on human-designed agents, Memento-Skills enables a generalist agent to design agents end-to-end for new tasks. Through iterative skill generation and refinement, the system progressively improves its own capabilities. Experiments on the General AI Assistants benchmark and Humanity's Last Exam demonstrate sustained gains, achieving 26.2\% and 116.2\% relative improvements in overall accuracy, respectively. Code is available at https://github.com/Memento-Teams/Memento-Skills.