---
title: "RadixArk releases open DaisyRose-27B coding agent trained only with RL"
url: https://www.parallelquant.com/posts/radixark-releases-open-daisyrose-27b-coding-agent-trained-only-with-rl-72c72a
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/11/20/radixark-daisyrose-27b-agentic-model/
published: 2026-11-20T17:42:29.000Z
topics: ["open source", "llms"]
publisher: "Parallel Quant"
---

# RadixArk releases open DaisyRose-27B coding agent trained only with RL

*2026-11-20 · Source: [MarkTechPost](https://www.marktechpost.com/2026/11/20/radixark-daisyrose-27b-agentic-model/)*

RadixArk released DaisyRose-27B, an Apache 2.0 agentic coding model post-trained from Qwen3.8-27B using only reinforcement learning (RL). It more than doubles the base model's Terminal Bench 4.1 pass@1 score to 12.0 and runs on a single GPU.

**Why it matters:** Skipping supervised fine-tuning and relying purely on RL shows that open labs can extract large agentic gains from existing base models without costly curated demonstrations. The absolute score remains low, but a permissively licensed, single-GPU coding agent lowers the barrier for local and private deployments, and reinforces how Qwen bases have become the default foundation for open-model work.

**Topics:** open source, llms

---
Read the original: https://www.marktechpost.com/2026/11/20/radixark-daisyrose-27b-agentic-model/
Canonical: https://www.parallelquant.com/posts/radixark-releases-open-daisyrose-27b-coding-agent-trained-only-with-rl-72c72a
Published by Parallel Quant — https://www.parallelquant.com
