paper-with-me

홈 › Papers

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

2026-05-05 · Siyuan Guo, Yali Du, Hechang Chen, Yi Chang, Jun Wang 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.

📄 PDF Abstract BibTeX arXiv:2605.06702

Code (0)

등록된 구현이 없습니다.

Tasks

Medical DiagnosisCode Generation

Similar Papers 제목 키워드 기반

Continual Reinforcement Learning with Multi-Timescale Replay

2020-04-16 · Christos Kaplanis, Claudia Clopath, Murray Shanahan

In this paper, we propose a multi-timescale replay (MTR) buffer for improving continual learning in RL agents faced with environments that are changing continuously over time at timescales that are unknown to the agent. …

Continual Learningcontinuous-controlContinuous Controlreinforcement-learning+2

Towards Continual Learning for Multilingual Machine Translation via Vocabulary Substitution

2021-03-11 · NAACL 2021 4 · Xavier Garcia, Noah Constant, Ankur P. Parikh, Orhan Firat

We propose a straightforward vocabulary adaptation scheme to extend the language capacity of multilingual machine translation models, paving the way towards efficient continual learning for multilingual machine translati…

Continual LearningMachine TranslationTranslation

COPAL: Continual Pruning in Large Language Generative Models

2024-05-02 · Srikanth Malla, Joon Hee Choi, Chiho Choi

Adapting pre-trained large language models to different domains in natural language processing requires two key considerations: high computational demands and model's inability to continual adaptation. To simultaneously …

Sensitivity

Continual Learning for Sequential Personalization of Small Language Models: A Stability Monitoring Analysis

2026-06-26 · Thomas S. Paula, Lucas S. Kupssinskü, Rodrigo C. Barros arxiv

Small Language Models (SLMs) are increasingly being considered for deployment on edge devices such as laptops, enabling private, low-latency, and locally personalized applications. However, personalization requires model…

Continual Learning

AuRA: Internalizing Audio Understanding into LLMs as LoRA

2026-06-09 · Bo Cheng, Lei Shi, Zhanyu Ma, Yuan Wu 외 arxiv

Recent efforts to extend large language models (LLMs) to speech inputs typically rely on cascaded ASR-LLM pipelines, end-to-end speech-language models, or bridge/distillation-based adaptation. While these routes respecti…