# Hark Labs explains agentic RL post-training with SGLang, Miles and Harbor

> Original title: SGLang, Miles and Harbor for agentic RL post-training.

- Source: LMSYS Org
- Published: 2026-11-07T02:08:53.000Z
- Bad Influence: https://badinfluence.news/items/nve5i6h5e3ilb6q1kefj8jmyf
- Original: https://x.com/lmsysorg/status/2118888388573200441

## Summary

Hark Labs authors Tianqi Liu and Jackie Yuan explain how SGLang, Miles and Harbor work together for agentic reinforcement learning post-training. The post is a short announcement that links to the full write-up.

## Post

SGLang, Miles and Harbor for agentic RL post-training.

Tianqi Liu and Jackie Yuan from @hark_labs bring the three together in “Agentic RL Post-Training with SGLang, Miles and Harbor.”

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWfL_eZaoAA-gxL.jpg&mode=thumb&exp=1794268800&sig=c946d65229501e90)