LangChain Launches LangSmith Fine-Tuning to Turn Agent Traces into Models
LangChain introduced LangSmith Fine-Tuning and the smithtune CLI, turning agent traces into SFT models without manual pipelines. In internal tests, OpenSWE Review accuracy rose from 62.9% to 81.5% with 29% fewer tool calls.
2026-10-01 ~ 2026-10-01 · 3 related posts
- LangChain launches LangSmith Fine-Tuning: turn agent traces into fine-tuned models via smithtune CLI — LangChain · 2026-10-01
- LangChain: fine-tuning on agent traces lifts OpenSWE Review precision to 81.5% with 29% fewer tool calls — LangChain · 2026-10-01
- LangChain Launches smithtune to Turn Agent Traces Into Fine-Tuned Models — LangChain · 2026-10-01