Memento-Skills：讓智能體設計智能體
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
我們推出Memento-Skills——一個通用且可持續學習的大型語言模型代理系統，其本質是能設計代理的元代理：該系統通過經驗積累自主構建、調整並優化任務專用代理。該系統基於具狀態提示的記憶強化學習框架，將可複用技能（以結構化Markdown文件形式存儲）作為持續演化的持久記憶。這些技能同時編碼行為與上下文，使代理能夠在交互過程中傳承知識。
系統從基礎技能（如網絡搜索和終端操作）起步，通過Memento~2~wang2025memento2提出的讀寫反射學習機制持續進化。在讀取階段，行為可訓練的技能路由器根據當前狀態提示選擇最相關技能；在寫入階段，代理根據新經驗更新擴充技能庫。這種閉環設計實現了無需更新LLM參數的持續學習，所有適應性調整均通過外部化技能與提示的演變來實現。
有別於依賴人工設計代理的傳統方法，Memento-Skills使通用代理能為新任務端到端地設計專用代理。通過迭代式技能生成與優化，系統持續提升自身能力。在通用AI助手基準測試與「人類終極考試」上的實驗顯示出持續性能增益，整體準確率分別實現26.2%和116.2%的相對提升。程式碼已開源於：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.