Snowflake AI Research Releases Open Source Arctic RL Backend

Original post

After many months of intense work the @Snowflake AI Research team is happy to present to you the new open source project: Arctic RL

https://www.snowflake.com/en/blog/engineering/arctic-rl-open-source-backend/

- Arctic RL integrates with VeRL and SkyRL today; enable ZoRRo with one config flag, no code changes required - ZoRRo delivers up to 6x actor-update acceleration and a 3.5x end-to-end training speedup, reducing Arctic-Text2SQL-R2 training from ~5 days to ~36 hours on 32 H200 GPUs - Arctic-Text2SQL-R2 achieved higher accuracy scores (48.7) than Gemini 3.1 Pro (47.9) and Claude 4.7 (47.3) on Snowflake's evaluated enterprise SQL benchmark under the tested conditions - Two open source recipes ship with this release: a text-to-SQL recipe that improved BIRD dev accuracy from 59.92% to 70.35%, and a multi-hop QA recipe that improved average accuracy from 69.6% to 72.3%

9:14 AM · Jun 29, 2026 · 1.2K Views

VIEWS1.6KBOOKMARKS21LIKES36RETWEETS3REPLIES1

Stas Bekman@StasBekman

In parallel we announce a new open source repo:

https://github.com/Snowflake-AI-Research/Arctic-Platform

This is the framework for very fast RL (and future other optimizations rolled into it)

It currently has all the code you need to use or integrate Arctic RL into RL frameworks, with SkyRL and Verl available and more framework integrations coming.

Please kindly spread the word! Thank you!

2h1.6K3621

Novavad@Nova_vad

@StasBekman @Snowflake love seeing major orgs open-source infrastructure like this. reduces friction for builders

the benchmark improvements are solid. open-source projects that ship benchmarks (not just code) change the game. that's how people actually use and trust your work

2h11

validate.qa@Validate_QA

@StasBekman @Snowflake open source rl infra from a team that size is wild. good luck shipping it