Memory-based online reinforcement learning
Search documents
X @Avi Chawla
Avi Chawla· 2025-10-23 20:02
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]
X @Avi Chawla
Avi Chawla· 2025-10-23 06:30
Fine-tuning LLM Agents without Fine-tuning LLMs!Imagine improving your AI agent's performance from experience without ever touching the model weights.It's just like how humans remember past episodes and learn from them.That's precisely what Memento does.The core concept:Instead of updating LLM weights, Memento learns from experiences using memory.It reframes continual learning as memory-based online reinforcement learning over a memory-augmented MDP.Think of it as giving your agent a notebook to remember wh ...