The paper introduces a compositional continual learning benchmark for world models in robot manipulation, designed to isolate knowledge reuse from learning speed and capacity. Tasks are curated to combine previously seen action and perception components, allowing analysis of how different modalities affect reuse. Experiments show that modular world models better balance reuse and forgetting than conventional methods, yet none fully solve the challenge, highlighting the need for models explicitly built to reuse knowledge without forgetting.
By Haoyu Zhou, Joe Watson, Anson Lei, Ingmar Posner
arXiv:2608. 13600v1 Announce Type: cross Abstract: We study Evolution Strategies (ES) for continual control, where agents must adapt to changing tasks without forgetting previous ones.
By Nicola Pitzalis, Eleni Nisioti, Antonio Carta, Davide Bacciu, Andrea Cossu
arXiv:2601.22475v2 Announce Type: replace
Abstract: Building a generalist robot policy requires continuously integrating new skills while preserving previously acquired behaviors. Directly optimizing...
By Qijun He, Yuxuan Li, Mingqi Yuan, Xiaoquan Sun, Wen-Tse Chen, Jeff Schneider, Jiayu Chen
The paper introduces Harness Continual Learning (HCL), a paradigm where an agent’s state evolves through prompts, memories, tools, skills, and routing rules while keeping the underlying foundation model frozen. HCL defines harness-level forgetting and proposes a guarded evolution process involving a Continual Optimizer and Evaluator to ensure improvements without losing prior behavior. Experiments across textual reasoning, multimodal perception, and open‑world interaction show over 10% performance gains and demonstrate how the stability–plasticity trade‑off can be explicitly tuned.
By Borui Kang, Jinrui Gu, Junhan Lv, Wenbin Li, Lei Wang, Yang Gao
Continual learning, the ability to learn from sequential experience while retaining and adapting prior knowledge, is central to intelligent systems operating in changing environments. However, convent...
The paper introduces Harness Continual Learning (HCL), a paradigm where an agent’s state evolves through prompts, memories, tools, skills, and routing rules while keeping the foundation model frozen. HCL defines harness-level forgetting and proposes guarded harness evolution with a Continual Optimizer and Evaluator to balance improvement, retention, and validity. Experiments across textual reasoning, multimodal perception, and open‑world interaction show over 10% performance gains and demonstrate explicit control over the stability–plasticity trade‑off.
arXiv:2609.25146v1 Announce Type: new
Abstract: Continual learning, the ability to learn from sequential experience while retaining and adapting prior knowledge, is central to intelligent systems ope...
By Hongwei Yan, Kanglei Zhou, Qi Cheng, Weiyi Dong, Chunyan Lan, Guanglong Sun, Jun Zhou, Qian Li, Yi Zhong, Liyuan Wang
Teach-and-Grow Learning (TGL) is an agent-centered architecture that transforms a few successful demonstrations into reusable Skill Blocks, enabling a robot to compose, execute, and revise behaviors in new scenes without task-specific policy retraining. The system maintains a Skill Library and structured Experience Memory to capture successes, failures, and repairs, allowing persistent reuse and agent-directed adaptation. Evaluation on the LIBERO benchmark shows state-of-the-art performance, and the authors propose a scaling-law hypothesis suggesting that accumulated reusable experience reduces future-task error and teaching demand following a power-law trend.
By Chang Nie, Zhe Liu, Hesheng Wang
The paper introduces SingularClip, a method that periodically clips the singular values of all weight matrices to prevent spectral collapse, a newly identified cause of plasticity loss in neural networks trained on nonstationary tasks. The authors empirically and theoretically analyze how growing anisotropy of singular values degrades the ability to fit new targets, and demonstrate that SingularClip outperforms baseline approaches in both continual supervised learning and deep reinforcement learning settings.
By Tyler Kastner, Nimrod De La Vega, Amir-massoud Farahmand
arXiv:2606. 00880v1 Announce Type: cross Abstract: Continual reinforcement learning aims to produce agents that learn not only to improve at their current tasks but also to adapt as task distributions change.
By Purab Seth, Neil Shah, Kunal Jha, Samuel J. Gershman, Max Kleiman-Weiner, Wilka Carvalho
arXiv:2606. 03598v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have achieved remarkable success in language-conditioned robotic manipulation.
By Ziyang Chen, Shaoguang Wang, Weiyu Guo, Qianyi Cai, He Zhang, Pengteng Li, Yiren Zhao, Yandong Guo
arXiv:2606. 26183v1 Announce Type: cross Abstract: Building a generalist robot that can leverage prior knowledge for continuous task adaptation remains a significant challenge.
By Zhihao Gu, Lin Wang