AI RESEARCH
Procedural-skill SFT across capacity tiers: A W-Shaped pre-SFT Trajectory and Regime-Asymmetric Mechanism on 0.8B-4B Qwen3.5 Models
arXiv CS.LG
•
ArXi:2605.11907v1 Announce Type: new We measure procedural-skill SFT contribution across three Qwen3.5 dense scales (0.8B, 2B, 4B) on a 200-task / 40-skill holdout, with Claude Haiku 4.5 as a frontier reference. The corpus is 353 rows of (task + procedural-skill block, Opus chain-of-thought, judge-pass) nstrations. \textbf{Main finding.} Under matched-path LLM-only scoring, the SFT-attributable procedural-$\Delta$ lift is roughly uniform across sizes: $+0.070$ / $+0.040$ / $+0.075$ at 0.8B / 2B / 4B.