4B Model BFCL Jumps 15%: Snowflake Proves Power of Mid-Tool Training

TheTuringPost · x · 2026-08-23

Snowflake's MidTool paper demonstrates that introducing tool learning during mid-training—before SFT and RL—significantly boosts model performance. The study constructed a 20.3B token corpus combining context-grounded examples and native agent trajectories.

Key Findings:

Limitation: All models scored 0% on the MCP-Universe web-search subset, indicating that learning tools/workflows is insufficient for long-horizon research tasks.

Original post →

More from coding & agent

coding & agent channel →