# CRL-VLA: Continual Vision-Language-Action Learning Source: [CRL-VLA: Continual Vision-Language-Action Learning]() Collection index: [llms.txt]() Data updated: 2026-02-05T05:00:14.183Z Authors: Qixin Zeng, Shuo Zhang, Hongyin Zhang, Renjie Wang, Han Zhao, Libang Zhao, Runze Li, Donglin Wang, Chao Huang Published: 2026-02-03T12:09:53.000Z ## Abstract Lifelong learning is critical for embodied agents in open-world environments, where reinforcement learning fine-tuning has emerged as an important paradigm to enable Vision-Language-Action (VLA) models to master dexterous manipulation through environmental interaction. Thus, Continual Reinforcement Learning (CRL) is a promising pathway for deploying VLA models in lifelong robotic scenarios, yet balancing stability (retaining old skills) and plasticity (learning new ones) remains a formidable challenge for existing methods. We introduce CRL-VLA, a framework for continual post-training of VLA models with rigorous theoretical bounds. We derive a unified performance bound linking the stability-plasticity trade-off to goal-conditioned advantage magnitude, scaled by policy divergence. CRL-VLA resolves this dilemma via asymmetric regulation: constraining advantage magnitudes on prior tasks while enabling controlled growth on new tasks. This is realized through a simple but effective dual-critic architecture with novel Goal-Conditioned Value Formulation (GCVF), where a frozen critic anchors semantic consistency and a trainable estimator drives adaptation. Experiments on the LIBERO benchmark demonstrate that CRL-VLA effectively harmonizes these conflicting objectives, outperforming baselines in both anti-forgetting and forward adaptation. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Vision-Language-Action Learning on LIBERO Multi-task scenario](): Vision-Language-Action Learning; LIBERO Multi-task scenario; FAR: 0.74. - [Continual Vision-Language-Action Learning on LIBERO single-task learning scenario](): Continual Vision-Language-Action Learning; LIBERO single-task learning scenario; FAR: 0.98. ## Original sources and implementation [Original paper]() [PDF]()