Improve your agent’s tool-calling accuracy with SFT and DPO on Amazon SageMaker AI
Combining SFT and DPO on SageMaker AI improves a small model's tool-calling accuracy for agents.
“When an agent picks the wrong tool, formats parameters incorrectly, or breaks a workflow chain, task completion times grow, error rates rise, support costs increase, and user experiences degrade.”
An AWS tutorial demonstrates using Supervised Fine-Tuning and Direct Preference Optimization together on SageMaker AI to boost the tool-calling accuracy of a small language model (Qwen3 1.7B). It matters because reliable tool selection is a key bottleneck for moving agentic applications from pilot to production, but the post is a how-to guide rather than a major industry announcement.