# CaPtain: A pipeline for post-training small open VLMs into code-as-policy robot agents

- Source: arXiv cs.RO
- Published: 2026-11-02T05:00:00.000Z
- RoboHot: https://robohot.news/en/items/oq1dkx5pu7qpj3lin3dc2py48
- Original: https://arxiv.org/abs/2610.40799

## Summary

CaPtain proposes an open post-training pipeline that trains small open vision-language models (VLMs) into code-as-policy (CaP) robot agents, without relying on VLAs, frontier models, or privileged state at test time. The pipeline first performs supervised fine-tuning on synthetic trajectories generated by GPT-6 Astra, then applies multi-turn reinforcement learning, introducing a physics critic that reads simulator privileged state to assign credit to each request.