LangChain: fine-tuning on agent traces lifts OpenSWE Review precision to 81.5% with 29% fewer tool calls
LangChain · x · 2026-10-01
LangChain ran LangSmith Fine-Tuning on two of its own agents:
- OpenSWE Review precision rose from 62.9% to 81.5% with 29% fewer tool calls per review
- Engine, fine-tuned on Kimi K3, beat both the base model and GPT-5.6 Sol on their issue-detection benchmark
The takeaway: fine-tuning specialized models on your own agent trajectories can outperform general frontier models at lower cost and latency.
Related event: LangChain Launches LangSmith Fine-Tuning to Turn Agent Traces into Models(3 posts)→
More from coding & agent
- We shipped 2,000 MCP integrations. Enterprise customers wanted only their own 20 — alexcovo_eth · 2026-10-02
- "The repos are now the prompts, 100%": Ofir Press on AI coding's shifting context — OfirPress · 2026-10-02
- OpenHands announces SOC 2 Type II compliance for enterprise agent security — rajistics · 2026-10-02
- Grady Booch: Coding agents write code well, but architecture still needs human judgment — Grady_Booch · 2026-10-02
- Jev pitches 'decision primitives': models plugging into logic without text — hardimanjames · 2026-10-02
- LangChain's Sproul: agent core pattern unchanged for a year, "we've been at AGI for four months" — BraceSproul · 2026-10-02