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.
More from coding & agent
- Clinician-Reviewed Child Psychiatry MCP Library Launches on Glama — modelcontextprotocol · 2026-09-25
- Brainiall MCP Server Brings Phoneme-Level Speech Assessment to Agents — modelcontextprotocol · 2026-09-25
- Plan Mode rework: customizable prompt, shareable modes, rebindable Shift+Tab — trq212 · 2026-09-25
- Firecrawl raises $75M Series B, targets $100M ARR with fewer than 50 people — devdigest · 2026-09-25
- Hill Sampling: Condition on the Best Verified Solution, Generate 512 Parallel Edits, Repeat — LChoshen · 2026-09-25
- Free Public MCP Server Exposes Canadian Privacy Law Data: 263 Terms, CAI Cases — masiha97 · 2026-09-25