交通信号控制（TSC）对于提升城市机动性和缓解拥堵至关重要。尽管路侧摄像头在信号交叉口广泛部署，并能提供丰富的动态交通视觉观测数据，但现有的 TSC 方法通常依赖人工设计的交通状态或独立的感知模块，导致物理观测与控制决策之间存在脱节。我们提出了 VLALight，这是首个基于多视角路侧视频实现端到端交通信号控制的视觉-语言-动作（VLA）模型。VLALight 通过多目标时空交通推理和跨交叉口的拓扑感知协同感知，直接将视觉观测映射为协调的信号动作。为了建立这一能力，我们开发了一种两阶段监督冷启动训练策略，分别用于视觉交通理解和信号决策，随后采用协同智能体强化学习，联合优化局部控制和全网交通效率。此外，VLALight 引入了自适应快慢推理模式，使策略仅在额外深思熟虑能带来足够控制收益时分配更深层的推理资源。通过平衡的模式感知回滚和相对优势优化，VLALight 学会了在决策质量和推理成本之间进行权衡。在三个城市网络的七个真实世界交通流数据集上进行的大量实验表明，VLALight 始终优于基于交通工程、强化学习以及大语言模型/视觉语言模型的基线方法。消融研究验证了协同感知、网络级优化和自适应推理的有效性。这些结果展示了 VLA 模型在现实世界物理交通控制中的潜力。我们的项目代码可在 htt 获取

Traffic signal control (TSC) is essential for improving urban mobility and reducing congestion. Although roadside cameras are widely deployed at signalized intersections and provide rich visual observations of evolving traffic, existing TSC methods typically rely on manually engineered traffic states or separate perception modules, creating a gap between physical observations and control decisions. We present VLALight, the first vision-language-action (VLA) model for end-to-end traffic signal control from multi-view roadside videos. VLALight directly maps visual observations to coordinated signal actions through multi-target spatiotemporal traffic reasoning and topology-aware cooperative perception across intersections. To establish this capability, we develop a two-stage supervised cold-start training strategy for visual traffic understanding and signal decision-making, followed by cooperative agentic reinforcement learning that jointly optimizes local control and network-wide traffic efficiency. Furthermore, VLALight introduces adaptive fast and slow reasoning modes, enabling the policy to allocate deeper reasoning only when additional deliberation provides sufficient control benefits. Through balanced mode-aware rollouts and relative advantage optimization, VLALight learns to trade off decision quality and inference cost. Extensive experiments on seven real-world traffic-flow datasets across three urban networks demonstrate that VLALight consistently outperforms transportation-based, RL-based, and LLM/VLM-based baselines. Ablation studies validate the effectiveness of cooperative perception, network-level optimization, and adaptive reasoning. These results demonstrate the potential of VLA models for real-world physical traffic control. Our project is available at https://github.com/usail-hkust/VLALight.git.