Skip to content
AI News HubLIVE
Original source2 min read

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

Summary

This paper formalizes deployment-time learning (DTL) as a third stage in the LLM lifecycle and presents CASCADE, a framework that equips LLM agents with an evolving episodic memory and contextual bandit mechanism for experience reuse without modifying parameters. Across 16 tasks, CASCADE improves macro-averaged success rate by 20.9% over zero-shot prompting.

SourcearXiv AIAuthor: Siyuan Guo, Yali Du, Hechang Chen, Yi Chang, Jun Wang
CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2605.06702] CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment

[Submitted on 5 May 2026]

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

View a PDF of the paper titled CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment, by Siyuan Guo and 4 other authors

View PDF HTML (experimental)

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.

Subjects:

Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG)

Cite as: arXiv:2605.06702 [cs.AI]

(or arXiv:2605.06702v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2605.06702

arXiv-issued DOI via DataCite

Submission history

From: Siyuan Guo [view email] [v1] Tue, 5 May 2026 12:16:59 UTC (3,441 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment, by Siyuan Guo and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-05

Change to browse by:

cs cs.CL cs.LG

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Formalizes deployment-time learning (DTL) as a new phase in the LLM lifecycle for post-deployment adaptation.
  • CASCADE framework uses episodic memory and contextual bandits for principled exploration-exploitation trade-offs and no-regret guarantees.
  • Achieves 20.9% improvement in macro-averaged success rate over zero-shot on 16 diverse tasks.
  • Enables continuous improvement without parameter modification by accumulating and selecting task-relevant cases.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Models