Memento-Skills: Let Agents Design Agents

arXiv:2603.18743v1 Announce Type: new
Abstract: We introduce emphMemento-Skills, a generalist, continually-learnable LLM agent system that functions as an emphagent-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 emphstateful 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 emphRead–Write Reflective Learning mechanism introduced in emphMemento~2~citewang2025memento2. In the emphread phase, a behaviour-trainable skill router selects the most relevant skill conditioned on the current stateful prompt; in the emphwrite phase, the agent updates and expands its skill library based on new experience. This closed-loop design enables emphcontinual 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 emphdesign agents end-to-end for new tasks. Through iterative skill generation and refinement, the system progressively improves its own capabilities. Experiments on the emphGeneral AI Assistants benchmark and emphHumanity’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.