From Distillation to Reinforcement Fine-Tuning: Hill-Climbing in Microsoft Foundry

TL; DR: Hill climbing means improving the deployable model package one measured step at a time across quality, latency, and cost. SFT made this workload cheaper, but did not transfer the teacher's planning quality. Adding explicit reasoning produced the major quality gain. RFT in Microsoft Foundry then retained near-teacher quality, achieved 100% feasibility on 150 held-out scenarios, and reduced token cost from $0.09975 to $0.03101 per scenario. Jump to the measured hill climb . What you will learn How to frame model customization as a measurable hill climb rather than a one-shot training dec