CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment

This paper introduces Deployment-Time Learning (DTL) as a new stage for LLMs, allowing them to continually adapt from experience post-training without modifying core parameters. It presents CASCADE, a framework that uses an explicit, evolving episodic memory for LLM agents, formalizing experience reuse as a contextual bandit problem with no-regret guarantees.