# CaPtain: A Post-Training Pipeline for Code-as-Policy Robot Agents

- Source: HuggingFace Daily Papers
- Published: 2026-10-29T00:00:00.000Z
- RoboHot: https://robohot.news/en/items/x3lgce0ptj469nw06s3ogcxon
- Original: https://huggingface.co/papers/2610.40799

## Summary

CaPtain proposes an open post-training pipeline that trains small open vision-language models such as Qwen3.5-4B into code-as-policy (CaP) robot agents that do not rely on VLAs, frontier models, or privileged state at test time.

## Why it matters

The work proposes using a physical critic to assign credit across multi-turn code policies and presents a complete training procedure for small models on LIBERO and real robots.