让机器人通过反思动作后果，提升跨环境任务泛化能力。
Reflective VLA: In-Context Action Consequences Make VLAs Generalize
- 用观察-动作-结果三元组构建上下文，增强决策依据。
- 在LIBERO-Plus上成功率提升5.4个百分点，Hard版提升4.2点。
- 适合需要跨场景部署的具身智能任务研究者。
多数视觉-语言-动作（VLA）模型是反应式的：仅根据当前指令和观测预测下一步动作，隐含假设当前观测已完整描述动作相关状态。但在具身控制中，相机与机器人几何关系、校准偏差或系统性执行偏移等具身因素常无法从单次观测中识别，导致反应式策略难以可靠区分这些因素，从而在训练环境过拟合，部署时泛化能力差。本文提出反射式VLA（Reflective VLA），将每一步决策基于包含观察-动作-后果的三元组上下文。每个三元组不仅记录机器人观测与执行的动作，还记录之后场景的变化，揭示动作到观测效果的部署特异性映射。架构上，所有模态通过共享注意力的视觉语言模型（VLM）处理，使动作专家直接推理历史三元组与当前观测。块因果掩码支持并行多帧训练且无信息泄露，并实现带缓存的实时推理。在标准LIBERO和SimplerEnv-Bridge上，反射式VLA保持强分布内性能；在分布外的LIBERO-Plus和更难的LIBERO-Plus-Hard上，相比匹配的反应式基线分别提升平均成功率5.4和4.2个百分点。消融实验表明，行动后果本身（而非仅增加上下文长度）才是跨环境泛化的关键。
原文摘要 · Abstract (English)
Most vision-language-action (VLA) models are reactive: they predict the next action from the current instruction and observation, implicitly assuming that the current observation fully specifies the action-relevant state. In embodied control, however, embodiment-specific factors such as camera-to-robot geometry, robot calibration, or systematic actuation bias are often hard to identify from a single observation. As a result, reactive policies cannot reliably disambiguate these factors in general, overfitting to training environments and generalizing poorly at deployment. We propose Reflective VLA, which conditions each decision on a context of observation-action-consequence triplets. Each triplet records not only what the robot observed and executed, but also how the scene changed afterward, exposing the deployment-specific mapping from actions to observed effects. Architecturally, Reflective VLA routes all observation modalities through the VLM under shared attention, so the action expert reasons directly over past triplets and the current observation. A block-causal mask enables parallel multi-frame training without leakage and supports KV-cached real-time inference. On standard LIBERO and SimplerEnv-Bridge, Reflective VLA preserves strong in-distribution performance. Under distribution shift on LIBERO-Plus and the harder LIBERO-Plus-Hard, it improves average success rate by 5.4 and 4.2 percentage points over a matched reactive baseline. Ablations with a matched history-only baseline further show that action consequences -- rather than additional context length alone -- are the key to cross-environment generalization. Project page: https://lianqing11.github.io/reflective-vla-page/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。