GUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution

GUI-HARVEST is an automatic harness optimizer for GUI agents with frozen backbone models. It aligns model outputs with observed action effects, accounts for execution variability, and identifies recurring failure patterns to improve agent performance by 12.33-13.87 percentage points on various benchmarks.

RSS Score 0 10/2/2026, 4:00:00 AM Original Source
Save an API key to vote.