AWS SageMaker AI enhances agent tool-calling with SFT and DPO

By PulseAugur Editorial · [2 sources] · 2026-06-03 15:56

Amazon SageMaker AI is now offering a method to enhance the tool-calling accuracy of AI agents. This is achieved by employing Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) techniques. The process involves training a small language model (SLM) using curated datasets and human feedback to improve its ability to select the correct tools for tasks. AI

IMPACT Enhances AI agent reliability and efficiency, potentially reducing operational costs for businesses deploying agentic applications.

RANK_REASON The article describes a new method for improving AI agent capabilities on an existing platform, rather than a novel model release.

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

AWS Machine Learning Blog TIER_1 English(EN) · Amin Dashti · 2026-06-03 15:56

Improve your agent’s tool-calling accuracy with SFT and DPO on Amazon SageMaker AI

In this post, you learn how to use Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) together to improve the tool-calling accuracy of a small language model (SLM). The example uses Amazon SageMaker AI training jobs, so you can focus on training code instead of…
Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] · 2026-06-03 16:01

🤖 Improve your agent’s tool-calling accuracy with SFT and DPO on Amazon SageMaker AI In this post, you learn how to use Supervised Fine-Tuning (SFT) and Direct

🤖 Improve your agent’s tool-calling accuracy with SFT and DPO on Amazon SageMaker AI In this post, you learn how to use Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) together to improve the tool-calling accuracy of a small language model (SLM). The example…

LINKS aws.amazon.com/…/improve-your-agents-tool…