Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

The research introduces Memento, a novel approach for adaptive Large Language Model (LLM) agents that enables continuous learning without requiring fine-tuning of the base LLM parameters. This method leverages a memory-based online reinforcement learning framework, formally defined as a Memory-augmented Markov Decision Process (M-MDP), which stores past experiences in an episodic memory and continually updates a neural case-selection policy. Memento utilizes a planner-executor architecture and a comprehensive suite of tools, demonstrating state-of-the-art performance on various benchmarks, including GAIA, DeepResearcher, and SimpleQA. The ablation studies confirm that both parametric and non-parametric case-based reasoning (CBR) are crucial for significant performance gains and effective generalization to out-of-distribution tasks.