Harness Adapters Launch: LoRA Boosts Qwen3.8-27B Coding Agent Performance
Hugging Face's harness-hub team released the first Harness Adapters, LoRA adapters trained with safe RL to adapt models like Qwen3.8-27B to their agent harness, doubling solve rates on Pi without changing the harness.
2026-11-17 ~ 2026-11-17 · 3 related posts
- Episode 1: Hugging Face's Harness Adapters: Cheap LoRA+RL Tune Small Models per Agent Framework(2026-11-06, 18 posts)
- Episode 2: Harness Adapters Launch: LoRA Boosts Qwen3.8-27B Coding Agent Performance(2026-11-17, 3 posts)
- Pi harness adapter via RL: SWE-bench Pro 29.4%→62.7% with 55% fewer tool calls — yb2698 · 2026-11-17
- harness-hub releases first RL-trained harness adapter for agentic coding, full recipe coming Friday — yb2698 · 2026-11-17
- Harness Adapters: RL-trained LoRA lifts Qwen3.8-27B on Pi from 29% to 63% on SWE-bench Pro — LysandreJik · 2026-11-17