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

arXiv: https://arxiv.org/abs/2605.06702 · HTML: https://mlsanity.com/paper/2605.06702/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 133 references that are in the map.
- First posted on arXiv 5 May 2026.

## Builds on (most cited first, 23 of 23)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [Memento: Fine-tuning LLM Agents without Fine-tuning LLMs](https://mlsanity.com/paper/2508.16153/) (2025)
- [Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving](https://mlsanity.com/paper/2507.06229/) (2025)
- [Agent Learning via Early Experience](https://mlsanity.com/paper/2510.08558/) (2025)
- [Memento-Skills: Let Agents Design Agents](https://mlsanity.com/paper/2603.18743/) (2026)
- [FLEX: Continuous Agent Evolution via Forward Learning from Experience](https://mlsanity.com/paper/2511.06449/) (2025)
- [Feedback Descent: Open-Ended Text Optimization via Pairwise Comparison](https://mlsanity.com/paper/2511.07919/) (2025)
- [Large Language Model Distilling Medication Recommendation Model](https://mlsanity.com/paper/2402.02803/) (2024)
- [GEM: A Gym for Agentic LLMs](https://mlsanity.com/paper/2510.01051/) (2025)
- [Online Multi-LLM Selection via Contextual Bandits under Unstructured Context Evolution](https://mlsanity.com/paper/2506.17670/) (2025)
- [EHR-R1: A Reasoning-Enhanced Foundational Language Model for Electronic Health Record Analysis](https://mlsanity.com/paper/2510.25628/) (2025)
- [Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through Likelihood Matching](https://mlsanity.com/paper/1901.08612/) (2019)
- [Neural Logistic Bandits](https://mlsanity.com/paper/2505.02069/) (2025)
- [Memento 2: Learning by Stateful Reflective Memory](https://mlsanity.com/paper/2512.22716/) (2025)
- [Case-Based Reasoning Enhances the Predictive Power of LLMs in Drug-Drug Interaction](https://mlsanity.com/paper/2505.23034/) (2025)
- [LogReasoner: Empowering LLMs with Expert-like Coarse-to-Fine Reasoning for Automated Log Analysis](https://mlsanity.com/paper/2509.20798/) (2025)

## Built on by (most cited first, 1 of 1)

- [Recurrent Harness for Agentic Continual Learning](https://mlsanity.com/paper/2610.12668/) (2026)

## Abstract (arXiv)

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.