QLORA SFT Distillation Effects on Qwen3.6 27B Agentic Coding Harness Fluency

Thomas Kim's research explores the impact of QLoRA SFT distillation on the Qwen3.6 27B model, particularly focusing on agentic coding harness fluency via Terminal-Bench 2.0 evaluations. The study investigates how harness-specific fine-tuning can alter model behavior, emphasizing the sensitivity of these changes to training traces, reasoning formats, and harness interfaces. The research tested various harnesses, including Codex CLI, OpenHands, and Pi, finding that the base Qwen3.6 27B model generally performed the best, although the v2 reasoning-distilled model showed improved task decomposition and validation. However, the v2 model also exhibited a tendency to over-explore and time out due to a shorter timeout period compared to the base model. The experiments underscore that while reasoning distillation may enhance certain forms of harness fluency, it can also lead to increased exploratory behavior that may not always be beneficial.

Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.