LIVE
Anduril CEO Palmer Luckey Calls for Jensen Huang’s Reinstatement at Nvidia DC Studios pivots strategy under Skydance leadership US Tightens Export Controls on AI Chips Amid Smuggling Concerns Amazon Launches SageMaker JumpStart Model Leaderboard for Standardized AI Comparisons Amazon Bedrock AgentCore Identity Adds Support for Private Certificate Authorities Take-Two CEO Strauss Zelnick Defends Hands-Off Approach as GTA VI Debuts Microsoft Unveils Windows Server 2028 with Security-First Default Configuration Google Expands Interactive World-Building with Genie 4 Launch Navigating Rust's Orphan Rule: Strategies for Foreign Type Implementation Salesforce Optimizes Global AI Model Inference with Amazon SageMaker Anduril CEO Palmer Luckey Calls for Jensen Huang’s Reinstatement at Nvidia DC Studios pivots strategy under Skydance leadership US Tightens Export Controls on AI Chips Amid Smuggling Concerns Amazon Launches SageMaker JumpStart Model Leaderboard for Standardized AI Comparisons Amazon Bedrock AgentCore Identity Adds Support for Private Certificate Authorities Take-Two CEO Strauss Zelnick Defends Hands-Off Approach as GTA VI Debuts Microsoft Unveils Windows Server 2028 with Security-First Default Configuration Google Expands Interactive World-Building with Genie 4 Launch Navigating Rust's Orphan Rule: Strategies for Foreign Type Implementation Salesforce Optimizes Global AI Model Inference with Amazon SageMaker

RadixArk Releases DaisyRose-27B Model Using New Reinforcement Learning Framework

🔌 Chips & Hardware 1 min read 👁 0

RadixArk has launched DaisyRose-27B, a model built on Qwen3.8-27B that utilizes a new reinforcement learning framework to significantly improve performance on long-horizon agent tasks.

RadixArk Releases DaisyRose-27B Model Using New Reinforcement Learning Framework🔌Chips & Hardware

Photo: Hacker News Front Page

Key points

  • DaisyRose-27B doubles Terminal-Bench 4.1 performance compared to its base model.
  • The Miles reinforcement learning framework enables asynchronous training to improve GPU utilization.
  • Custom sandboxing infrastructure reduced cloud costs by 80% during the nine-week training project.

RadixArk has unveiled DaisyRose-27B, its debut model developed by fine-tuning the Qwen3.8-27B base model. The project utilized a proprietary reinforcement learning framework called Miles, which allowed the team to train the model on 1,200 curated long-horizon tasks over an 18-day period using 144 H200 GPUs. According to the company, this process improved the model's performance on the Terminal-Bench 4.1 benchmark from 5.6% to 12.0%.

The training process was designed for high efficiency, achieving a 57% reduction in training costs compared to standard open-source trainers. By employing an asynchronous training mode, the system allowed the agent to continue working while the model learned, reaching a throughput of 16,800 tokens per second. The team also developed a custom sandboxing service to manage nearly one million task environments, reporting that the infrastructure was 80% cheaper than typical cloud alternatives.

RadixArk is now making the DaisyRose-27B model available in multiple formats, including BF16, FP8, and NVFP4, via Hugging Face. Additionally, the Miles reinforcement learning framework has been released as an open-source tool for other developers to utilize in training their own specialized agents.

Source Hacker News Front Page — radixark.com/blog/daisyrose-27b ↗

Contact the newsroom

Got a tip, a proposal or a partnership question? Write to us and we will reply shortly.