ZAP：纯仿真训练的机器人策略，零真实数据达到 96.7% 真实任务成功率
Pretraining Knows What, Simulation Teaches How: Compositional Generalization in a Sim-Trained Robot Agent
不用一条真实机器人数据，27B 视觉语言模型仿真里练出来就能 96.7% 完成真实任务，还比 GPT-6 Astra 便宜 17 倍，机器人方向值得看看这篇。
研究者提出 Zero-real Agent Policy（ZAP），用预训练的 27B 视觉语言模型通过工具接口控制机器人。训练流程是先做监督微调，再用 GRPO 在简单仿真任务上强化学习，全程不使用真实世界机器人数据。在真实任务上 ZAP 达到 96.7% 成功率，与 GPT-6 Astra 持平，超过 MolmoAct2 VLA 的 33.3%，速度比 GPT-6 Astra 快 3 倍、成本低 17 倍。ZAP 能泛化到训练数据中没有的物体、目标和语言，包括在试管架上换孔放置、双臂空中传递试管、画井字棋和下国际象棋。迁移到未见过的单臂 Franka 上，在 RoboLab-120 上达到 55.9%，比领先的 VLA/WAM 基线高 4.9 个百分点。
Pretraining Knows What, Simulation Teaches How: Compositional Generalization in a Sim-Trained Robot Agent
A robot policy needs to understand what a task is asking for in a scene, and how to move the robot to accomplish that task. To achieve these two skills, we introduce Zero-real Agent Policy (ZAP), a recipe that teaches a small off-the-shelf vision-language model to control a robot via a simple tool harness. We use a pretrained 27B parameter model to bootstrap world understanding and reasoning, followed by supervised fine-tuning and GRPO on simple simulated tasks to teach it how to move the robot. Without any real-world robot data during training, ZAP reaches 96.7% success on real-world tasks, matching GPT-6 Astra in our harness and outperforming the MolmoAct2 VLA (33.3%), while running 3x faster and 17x cheaper than GPT-6 Astra. We demonstrate that ZAP also generalizes to completely new objects, goals, strategies, and language by seating a test tube in a rack (and choosing a different hole in the rack when prompted), handing a test tube between arms mid-air, drawing an X on a tic-tac-toe board, and playing chess. These goals and types of manipulation don't appear in our training data. Furthermore, ZAP also transfers to an unseen embodiment. On a single-arm Franka, ZAP reaches 55.9% on RoboLab-120, 4.9 percentage points ahead of the leading VLA/WAM baseline.