Cover Image

Beyond Retention: Orchestrating Structural Safety and Plasticity in Continual Learning for LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Meng, Fei
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Pareto Continual Learning: Preference-Conditioned Learning and Adaption for Dynamic Stability-Plasticity Trade-off
by: Lai, Song, et al.
Published: (2025)

A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safety
by: Li, Gang, et al.
Published: (2024)

Knowledge Retention for Continual Model-Based Reinforcement Learning
by: Sun, Yixiang, et al.
Published: (2025)

Self-Normalized Resets for Plasticity in Continual Learning
by: Farias, Vivek F., et al.
Published: (2024)

Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning
by: Lillo, Lute, et al.
Published: (2026)

Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning
by: Elsayed, Mohamed, et al.
Published: (2024)

Preserving Plasticity in Continual Learning with Adaptive Linearity Injection
by: Rohani, Seyed Roozbeh Razavi, et al.
Published: (2025)

Maintaining Plasticity in Continual Learning via Regenerative Regularization
by: Kumar, Saurabh, et al.
Published: (2023)

Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn
by: Tang, Hongyao, et al.
Published: (2025)

PLATE: Plasticity-Tunable Efficient Adapters for Geometry-Aware Continual Learning
by: Cosentino, Romain
Published: (2026)

Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs
by: Li, Xuancheng, et al.
Published: (2026)

MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition
by: Bao, Yifan, et al.
Published: (2026)

Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs
by: Bui, Ngoc, et al.
Published: (2025)

Safe Reinforcement Learning with Learned Non-Markovian Safety Constraints
by: Low, Siow Meng, et al.
Published: (2024)

SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting
by: Qiu, Haomiao, et al.
Published: (2025)

Breaking the Safety-Capability Tradeoff: Reinforcement Learning with Verifiable Rewards Maintains Safety Guardrails in LLMs
by: Cho, Dongkyu Derek, et al.
Published: (2025)

Reservoir Network with Structural Plasticity for Human Activity Recognition
by: Zyarah, Abdullah M., et al.
Published: (2025)

Experience Replay Addresses Loss of Plasticity in Continual Learning
by: Wang, Jiuqi, et al.
Published: (2025)

xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning
by: Qian, Cheng, et al.
Published: (2025)

Operator-Guided Invariance Learning for Continuous Reinforcement Learning
by: Zhang, Zuyuan, et al.
Published: (2026)

Rethinking Plasticity in Deep Reinforcement Learning
by: He, Zhiqiang
Published: (2026)

Memory Retention Is Not Enough to Master Memory Tasks in Reinforcement Learning
by: Shchendrigin, Oleg, et al.
Published: (2026)

Classifier-free guidance in LLMs Safety
by: Smirnov, Roman
Published: (2024)

PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer
by: Chen, Chang, et al.
Published: (2024)

COSMIR: Chain Orchestrated Structured Memory for Iterative Reasoning over Long Context
by: Gupta, Naman, et al.
Published: (2025)

DynamicGate MLP Conditional Computation via Learned Structural Dropout and Input Dependent Gating for Functional Plasticity
by: Choi, Yong Il
Published: (2026)

Understanding and Preserving Safety in Fine-Tuned LLMs
by: Zhang, Jiawen, et al.
Published: (2026)

Activation Function Design Sustains Plasticity in Continual Learning
by: Lillo, Lute, et al.
Published: (2025)

Self-Controlled Dynamic Expansion Model for Continual Learning
by: Wu, Runqing, et al.
Published: (2025)

Dream2Learn: Structured Generative Dreaming for Continual Learning
by: Calcagno, Salvatore, et al.
Published: (2026)

Provable Effects of Data Replay in Continual Learning: A Feature Learning Perspective
by: Ding, Meng, et al.
Published: (2026)

Continual Learning for Smart City: A Survey
by: Yang, Li, et al.
Published: (2024)

Primal Dual Continual Learning: Balancing Stability and Plasticity through Adaptive Memory Allocation
by: Elenter, Juan, et al.
Published: (2023)

Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning
by: Todorov, Aleksandar, et al.
Published: (2025)

Plasticity Loss in Deep Reinforcement Learning: A Survey
by: Klein, Timo, et al.
Published: (2024)

Semantic Context for Tool Orchestration
by: Müller, Robert
Published: (2025)

Energy-Structured Low-Rank Adaptation for Continual Learning
by: Li, Longhua, et al.
Published: (2026)

Memory-Statistics Tradeoff in Continual Learning with Structural Regularization
by: Li, Haoran, et al.
Published: (2025)

Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMs
by: Zhang, Dingkun, et al.
Published: (2025)

Adaptive Budget Allocation for Orthogonal-Subspace Adapter Tuning in LLMs Continual Learning
by: Wan, Zhiyi, et al.
Published: (2025)