LangSmith Fine-Tuning Turns Agent Traces Into Models: 9B Beats Frontier on Task Benchmark
Hacubu · x · 2026-10-22
LangChain launched LangSmith Fine-Tuning and smithtune, a CLI that turns LangSmith agent trajectories into fine-tuned models end-to-end: dataset creation, training via Fireworks or Baseten, and evaluation uploaded back to LangSmith. Currently supports SFT.
Corridor used the workflow to train Argos, a 9B model that scored highest among 14 models tested on their security-context benchmark. As hwchase17 notes, traces you already log are training data: keep the successful runs, fine-tune a small model on them, and it can beat frontier models on exactly your task at lower cost and latency.
More from coding & agent
- CreateOS x Stripe Hackathon Draws 59+ Projects Where Agents Write and Verify Their Own Code — jeff_weinstein · 2026-10-22
- v0 on Mobile: One Prompt Repaints a Car Simulator and Pushes to a Branch — fernandorojo · 2026-10-22
- Dev Warns: No CVE Scanning on Every PR in 2026 Means You Won't Make It — letandrewcook · 2026-10-22
- "You asked for better, it added a border": AI design skill meme goes viral — kieranklaassen · 2026-10-22
- Anthropic reportedly previews Claude Duet, a proactive agent built on Opus 5.5 — BLCNYY · 2026-10-22
- Replacing LLM routing calls with 15ms CPU encoders: workshop on deterministic routing — camerongreen95 · 2026-10-22