Baseten Loops fine-tunes open models on LangSmith traces for self-improving agents

BraceSproul · x · 2026-09-25

Baseten published an article on how LangChain's applied research team fine-tunes the models behind LangSmith Engine using Baseten Loops: agent traces from LangSmith become curated training data for fine-tuning open models.

Key points:

Original post →

More from coding & agent

coding & agent channel →