小模型写代码操控机器人，反超闭源大模型
机器人操控一直有个尴尬：要么请闭源大模型当大脑，要么用专门的视觉-动作模型，而开源小模型直接拉胯。这篇把「写代码控制机器人」这条路走通了：一个 4B 参数的开源小模型，零样本时成功率是 0%，用合成数据微调后到 55%，再加一轮强化学习冲到 73.8%，在部分任务上超过了用闭源前沿模型的方案。关键不是模型本身，而是训练方法：它引入了一个「物理裁判」，能读取模拟器里的真实状态(策略本身看不到)，给每一步操作打分——这解决了多轮强化学习里「动作做了好几步、结果最后才显现」的信用分配难题。它不是你明天能用的东西，但信号很明确：开源小模型+聪明的训练管线，正在逼近甚至反超闭源大模型在具身智能上的表现，而且不需要特权状态、不需要专用硬件。
📄 原文摘要(英文)
Across coding, web, and tool-use tasks, language-model agents are now routinely trained with the same recipe: supervised fine-tuning (SFT) to learn the interface, then multi-turn reinforcement learning (RL) to master it. Code-as-policy (CaP) casts robot manipulation in the same form, as the policy writes code against robot APIs and reads back the results, so the same recipe should apply. Yet existing CaP agents sidestep training: they either prompt closed frontier models or delegate manipulation to pre-trained vision-language-action models (VLAs) and high-level skills, while small open vision-language models (VLMs) fail outright. We present CaPtain, an open post-training pipeline that turns a small open VLM into a capable CaP agent, with no VLA, frontier model, or privileged state at test time. CaPtain trains and deploys the policy inside CaPtain-Harness, which exposes low-level perception, geometry, and guarded-motion primitives across simulation and real hardware. We first align the base model via SFT on synthetic trajectories generated with GPT-6 Astra, then apply multi-turn RL. Multi-turn RL must credit tens of agent requests, whose physical effects often surface turns later, from a single end-of-episode outcome. We therefore introduce a physical critic that reads privileged simulator state, never seen by the policy, and credits each request by how much it changes the predicted chance of success. Starting from Qwen3.5-4B (0% zero-shot), CaPtain-4B reaches 55.4% held-out LIBERO success after SFT and 73.8% after RL. On LIBERO-PRO, it reaches 78.5%, surpassing several frontier-model agents, and its RL gains persist across three perturbation suites (+17.6 to +21.2 points). Without target-domain training, it attains 83.3% on SimplerEnv WidowX, exceeds frontier models on CaP-Bench, and runs on a real robot after simulation-only adaptation. We release all code, data, and model weights.