# After VLA and WAM, what role does Harness play in embodied AI systems?

- Source: 深蓝AI · 微信公众号
- Published: 2026-10-24T01:48:00.000Z
- RoboHot: https://robohot.news/en/items/sszrvc6vpjuihf8dvkhfcmkoc
- Original: https://mp.weixin.qq.com/s?__biz=MzY4NjA5NTgyMQ==&mid=2247606003&idx=1&sn=9a5a34620251272fb022a76cdc2ef481&chksm=f2a69b93b7907beaab131f5784c66f45eef5c3917f8994c85effacc7a73aeaf23b0b4ce74ecf&scene=126&sessionid=1792928106#rd

## Summary

Deep Blue AI published an article outlining the division of labor among VLA, WAM, and Harness in embodied systems: VLA turns observations and goals into actions, WAM uses future-state prediction to aid action learning, and Harness organizes subtasks, capability invocation, and execution feedback.