Core Concept of Memento - Memento reframes continual learning as memory-based online reinforcement learning over a memory-augmented MDP, learning from experiences using memory instead of updating LLM weights [2] - Memento aims to improve AI agent performance from experience without fine-tuning LLM weights [1] Key Components - Case-Based Reasoning (CBR) decomposes complex tasks into sub-tasks and retrieves relevant past experiences [2] - Executor executes each subtask using MCP tools and records outcomes in memory for future reference [3] MCP Tools - MCP tools enable the executor to accomplish most real-world tasks [3] - MCP tools include Web research, Document handling, Safe Python execution, Data analysis, and Media processing [3]

Core Concept - Memento reframes continual learning as memory-based online reinforcement learning over a memory-augmented MDP, learning from experiences using memory instead of updating LLM weights [1] - The system uses Case-Based Reasoning (CBR) to decompose complex tasks into sub-tasks and retrieves relevant past experiences without needing gradients [1] System Components - The Executor executes each subtask using MCP tools and records outcomes in memory for future reference [1] - MCP tools enable the executor to accomplish most real-world tasks, including web research, document handling, safe Python execution, data analysis, and media processing [1] Potential Impact - The industry views this as a promising path toward building human-like agents [1]