LangChain launches LangSmith Fine-Tuning: train specialized models from your agent traces

LangChain · x · 2026-09-25

LangChain officially announced LangSmith Fine-Tuning and the smithtune CLI, now in public beta. Built in partnership with Baseten and FireworksAI, it lets LangSmith handle the entire fine-tuning process — using collected agent traces to train specialized models that cut cost and latency.

The team argues one of AI's hardest problems today is a data problem: turning raw trajectories into environments and curated trajectories to improve agents is difficult, since current agents aren't good at data curation. LangChain Labs aims to help teams close the end-to-end loop from raw data to better agents via post-training and harness engineering.

Related event: LangChain Launches LangSmith Fine-Tuning Beta: Turn Agent Traces into Custom Models(9 posts)→

Original post →

More from coding & agent

coding & agent channel →