In the News: September 10, 2026 (Extra 3)
In a Salesforce study, full-trajectory imitation from a stronger model cut weaker-model accuracy by 4 to 30 points across all seven tasks under an evolved harness.
Extra edition
Machine-readable
Download Markdown
Story
Full-trajectory imitation cut weaker-model accuracy across all seven tasks
The Salesforce AI Research team tested harness evolution and fine-tuning on seven enterprise agent tasks. A weaker model first evolved its own agent harness, including the system prompt, tool set, execution hooks, and context-management…
Read story →