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:
- Pipeline: traces -> curated data/environments -> fine-tuning infra -> continuously better agents
- LangChain Labs says Loops takes them from idea to training experiment in minutes
- The goal is for every team to own this loop with custom data, optimizing for intelligence, cost and latency
More from coding & agent
- User ditches GUI: local LLM now his main PC interface for installs, GRUB and more — Forward_Jackfruit813 · 2026-09-25
- Where an agent loop runs, how it fails, and how to build durable sessions — tempNull · 2026-09-25
- Community turns the Opus 5.5 pixel-art prompt into an open-source pixel-anims skill — majidmanzarpour · 2026-09-25
- Opus 5.5 + one prompt generates animated pixel art wizard purely in code — majidmanzarpour · 2026-09-25
- A visual harness for Claude Code: watching your agents work after hours — EricBuess · 2026-09-25
- How Jev, a new System 1 model, changes memory and context engineering — julianweisser · 2026-09-25