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

Authors: Siyuan Guo, Yali Du, Hechang Chen et al.

arXiv · PDF

Summary

CASCADE equips LLM agents with an episodic memory that accumulates, selects, and refines task-relevant examples during deployment—without changing model weights. The system treats experience reuse as a contextual bandit problem, balancing exploration (trying new strategies) and exploitation (using known good examples) with formal no-regret guarantees. Testing across 16 diverse tasks (medical diagnosis, legal analysis, code generation, tool use, embodied interaction), CASCADE improves macro-averaged success by 20.9% over zero-shot prompting and beats both gradient-based fine-tuning and other memory baselines.

Main takeaways:

• CASCADE enables "deployment-time learning" (DTL)—the model improves from experience after training ends, without parameter updates.
• It builds an explicit episodic memory of past cases and uses contextual bandit algorithms to decide which cases to reuse.
• Formal guarantees ensure long-term regret bounds (the system won't get stuck in bad strategies).
• Beats zero-shot by 20.9% on average and outperforms gradient-based and simpler memory baselines across 16 tasks.
• Positions deployment as an adaptive learning phase, not just static inference.

Relevance

Not directly related to my persona installation or marker-implantation work—this is about in-context learning and episodic memory during deployment. It's conceptually adjacent if I ever wanted to test whether persona behaviors can be installed or modulated via example selection rather than fine-tuning, but it's a different installation path than what I'm investigating.

Abstract

arXiv:2605.06702v1 Announce Type: new Abstract: Large language models (LLMs) have become a central foundation of modern artificial intelligence, yet their lifecycle remains constrained by a rigid separation between training and deployment, after which learning effectively ceases. This limitation contrasts with natural intelligence, which continually adapts through interaction with its environment. In this paper, we formalise deployment-time learning (DTL) as the third stage in the LLM lifecycle that enables LLM agents to improve from experience during deployment without modifying model parameters. We present CASCADE (CASe-based Continual Adaptation during DEployment), a general and principled framework that equips LLM agents with an explicit, evolving episodic memory. CASCADE formulates experience reuse as a contextual bandit problem, enabling principled exploration-exploitation trade-offs and establishing no-regret guarantees over long-term interactions. This design allows agents to accumulate, select, and refine task-relevant cases, transforming past experience into actionable knowledge. Across 16 diverse tasks spanning medical diagnosis, legal analysis, code generation, web search, tool use, and embodied interaction, CASCADE improves macro-averaged success rate by 20.9% over zero-shot prompting while consistently outperforming gradient-based and memory-based baselines. By reframing deployment as an adaptive learning process, this work establishes a foundation for continually improving AI systems.