Salesforce: Fine-tuning a weak model to copy Gemini drops success 15%; correcting its own failures works

rohanpaul_ai · x · 2026-09-22

Salesforce AI research finds that once an agent's prompts, tools, and workflow are tuned around a weaker model (Qwen3-Coder-30B-A3B), fine-tuning it to copy a stronger Gemini model makes things worse.

Lesson: tune the model without breaking the agent setup already working around it.

Related event: Salesforce: Imitating Stronger Models' Trajectories Hurts Agent Performance(2 posts)→

Original post →

More from coding & agent

coding & agent channel →