arXiv Machine Learning
Jul 7
RL Forgets! Towards Continual Policy Optimization
arXiv:2607. 04364v1 Announce Type: new Abstract: Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks.
ARROW: Augmented Replay for RObust World models
arXiv:2603. 11395v3 Announce Type: replace-cross Abstract: Continual reinforcement learning challenges agents to acquire new skills while retaining previously learned ones with the goal of improving performance in both past and future tasks.
Related stories
arXiv Machine Learning
2d ago
Replay on Demand: An Emergent Curriculum for Balancing Adaptation and Forgetting in Continued Pretraining
arXiv:2609.40089v1 Announce Type: new Abstract: Continued pretraining enables language models to adapt to new domains and knowledge, but often at the cost of forgetting previously acquired capabiliti...
arXiv Machine Learning
Jul 20
Rethinking Transfer in Continual Learning: A Replay-Based Realisation
arXiv:2607. 15587v1 Announce Type: new Abstract: Continual learning studies how deployed language models can continually acquire new tasks without expensive retraining from scratch.
arXiv Machine Learning
Jul 10
When Does Continual Learning Require Learning
arXiv:2607. 07847v1 Announce Type: new Abstract: As large language models (LLMs) become increasingly capable, the next question is how can we enable models to continually learn?
arXiv Machine Learning
Jun 2
Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning
arXiv:2606. 01379v1 Announce Type: new Abstract: While prompt-based parameter-efficient continual learning mitigates catastrophic forgetting by isolating task-specific prompts, this isolation also limits later tasks from improving earlier ones, leaving backward knowledge transfer underexplored.
arXiv AI
Jul 23
The World Model Remembers, the Actor Forgets: Dream Rehearsal for Continual Model-Based RL
arXiv:2607. 19749v1 Announce Type: cross Abstract: Model-based reinforcement-learning agents of the DreamerV3 family forget catastrophically when trained on task sequences, even when an unbounded replay buffer preserves every earlier experience.
arXiv Machine Learning
Jun 2
Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning
arXiv:2603. 11653v2 Announce Type: replace Abstract: Continual Reinforcement Learning (CRL) for Vision-Language-Action (VLA) models is a promising direction toward self-improving embodied agents that can adapt in openended, evolving environments.
arXiv Machine Learning
Sep 25
Beyond Forgetting: Diagnosing and Harnessing Shared Reasoning in Continual RLVR
The paper introduces Continual Reasoning Gym, a continual‑RLVR environment that sequences text and visual reasoning tasks. It finds that while sequential RLVR shows modest forgetting, its final performance lags behind multitask RLVR (MTRL) because forgetting explains only part of the gap. To bridge this, the authors propose Continual Prompt Replay (CPR), which replays previous‑task prompts and regenerates responses with the current policy, achieving on average MTRL‑level performance.
arXiv Machine Learning
Aug 18
Geometry of Forgetting: Representation Flux in Continual Learning
arXiv:2608. 15854v1 Announce Type: new Abstract: Catastrophic forgetting remains a fundamental obstacle to continual learning, where neural networks lose previously acquired knowledge while learning new tasks.
arXiv Machine Learning
Jun 9
Theoretical Foundations of Continual Learning via Drift-Plus-Penalty
arXiv:2606. 08452v1 Announce Type: new Abstract: In many real-world settings, data streams are nonstationary and arrive sequentially, requiring learning systems to adapt continuously without retraining from scratch.
arXiv Machine Learning
Jul 30
The Art of Not Forgetting A Local Learning Architecture for Continual Learning
arXiv:2607. 26523v1 Announce Type: new Abstract: We introduce CMP (Cognitive Memory Primitive), a continual-learning architecture that repre?
arXiv AI
Jun 9
Not Just After One: Sleep-Inspired Replay Prevents Catastrophic Forgetting After Sequential Tasks
arXiv:2606. 08447v1 Announce Type: cross Abstract: One of the critical limitations of artificial neural networks is their lack of ability to continually learn: training on new tasks often leads to interference and forgetting of the previous ones.