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
EmbodiedCLBench is the first benchmark designed to evaluate continual learning in embodied simulation environments, focusing on self‑evolving agents. The benchmark uses compositional generalization to test whether agents can learn basic tasks and then recombine those skills to solve more complex, unseen tasks. Experiments across various agent harnesses and learning methods reveal that while basic task experience improves performance on advanced tasks, this benefit does not scale with more learning samples and current agents fail to extract additional useful information.
By Jie Huang, Yanan Chen, Ruixun Liu, Kaichen He, Xinyi He, Rui Huang, Zilong Zheng, Zhenliang Zhang, Yiwu Zhong
Dream to Remember (D2R) is a continual learning framework that steers a frozen generalist robot policy toward new tasks while preserving previously acquired skills. It uses a pretrained world model to rehearse past tasks through imagined rollouts, eliminating the need for replay buffers or new data. Experiments on CALVIN, LIBERO, and a real Franka robot show that D2R can learn multiple tasks sequentially—often entirely in imagination—without catastrophic forgetting, outperforming traditional fine‑tuning methods.
By Bahey Tharwat, Iman Nematollahi, Marvin Alles, Xingyuan Zhang, Akshay L Chandra, Abhinav Valada
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
arXiv:2610.18038v2 Announce Type: replace-cross
Abstract: World action models (WAMs) built on pretrained video generation models adapt quickly to new robotic tasks, but they forget previously learned...
By Kaipeng Fang, Hangxu Liu, Chaojian Shi, Yunsong Zhou, Hongzi Zhu, Minyi Guo, Jingkuan Song, Lianli Gao
RIFAR is a new continual learning method for robots that uses reliability screening and drift-aware replay to mitigate forgetting while keeping storage low. It reconstructs past trajectories from short demonstration prefixes and employs a frozen inverse-dynamics model to verify action‑visual consistency. In experiments on LIBERO suites and real‑world tasks, RIFAR outperforms previous generative replay approaches, achieving high performance with only a small fraction of stored steps.
By Zirong Song, Zheng Lu, Haoran Liao, Wanqi Zhong, Yunhe Ni, Lijie Wang, Xiuying Chen
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?
By Anne Harrington, Nayan Saxena, Michael Murphy, Anastasia Borovykh, Zeyu Yun, Sridhar Kamath, Ara Eindra Kyi, Trevor Darrell, Jitendra Malik, Yutong Bai
arXiv:2610.18596v1 Announce Type: cross
Abstract: Reinforcement learning (RL) post-training improves robot foundation models (RFMs) beyond their demonstrations, but real-world deployment demands more...
By Changyeon Kim, Kimin Lee, Yashraj Narang, Yijie Guo
arXiv:2609.36691v1 Announce Type: new
Abstract: Manipulation behaviors vary widely across objects and scenes, but they share a small set of reusable skills, and planning with these skills helps embod...
By Jianshu Zhang, Ce Zhang, Xiyuan Yang, Chenwei Xu, Haoran Lu, Yijiang Li, Yaqi Xie, Katia P. Sycara, Han Liu
arXiv:2608. 03874v1 Announce Type: new Abstract: Modern agent frameworks equip large language models with external skill libraries to solve complex tasks.
By Tianyi Guan, Yiding Wang, Haotong Yang, Siyuan Cao, Shirui Liu, Yi Hu, Jiaqi Li, Muhan Zhang
ACCRUE is a continual off‑policy reinforcement learning framework designed for robot foundation models. It keeps lightweight actor and critic networks across tasks, reusing behavioral and value knowledge from previous RL stages while preserving prior behavior through actor distillation on a small set of retained episodes. Experiments on contact‑rich assembly tasks in simulation and on real robots show that ACCRUE speeds up learning of new tasks, nearly eliminates forgetting, and cuts real‑robot training time by 31.0% to 68.5%.
The paper investigates how model-based reinforcement learning can support continual learning by reusing prior knowledge. It introduces a contextual Markov decision process that separates behavioral and physical context, and studies zero‑shot reuse in FourRooms tasks using Dyna‑Q and TD‑MPC. The experiments show that zero‑shot reuse degrades under physical context changes and that this degradation is strongly tied to the observation representation, highlighting representation generalization as a key bottleneck.
By Amir Mesbah, Di Wu