Hugging Face releases RL-trained harness adapters for Qwen3.8-27B
Hugging Face trained one LoRA adapter per agent harness for Qwen3.8-27B and says the pi version lifts a Terminal-Bench 2.1 score from 39% to 55%.
Everything Gajitt has published about reinforcement learning.
1 storyHugging Face trained one LoRA adapter per agent harness for Qwen3.8-27B and says the pi version lifts a Terminal-Bench 2.1 score from 39% to 55%.