AgentENV
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 2
- RadixArk releases DaisyRose-27B agent model
RadixArk released DaisyRose-27B, its first model, built on Qwen3.8-27B and post-trained with reinforcement learning using Miles. The company says it trained the model on 1,200 curated long-horizon agent tasks over 18 days on 144 H200 GPUs, with sessions reaching 1M tokens. RadixArk reported that Terminal-Bench 4.1 pass@1 increased from 5.6% to 12.0%, alongside gains on other reasoning, instruction-following and coding benchmarks; Apache 2.0 BF16, FP8 and NVFP4 checkpoints are available.
Hacker News 首页(100+ 分) · 🔥 0 - Miles Runs Agentic RL Training on NVIDIA Vera CPUs
RadixArk partnered with NVIDIA to run its open-source Miles post-training framework end to end, with every isolated Firecracker sandbox hosted on NVIDIA Vera CPUs. The reported run trained GLM-4.7-Flash for 68 steps across more than 2,400 Terminal-Bench and SWE-bench episodes in synchronous and fully asynchronous modes; one gRPC task’s pass rate rose from 40% to 82% between training halves. RadixArk also compared Vera with AMD EPYC Turin and Intel Xeon 61 systems, reporting 12% faster episodes under tested busy-server conditions.
LMSYS Blog · 🔥 0
Experience and discussion from the community
Share my AgentENV experienceAsk about AgentENV
Nobody has shared their experience with AgentENV yet.