Get the latest tech news
Skyvern Browser Agent 2.0: How We Reached State of the Art in Evals
We’ve been working hard cooking up something new to share with you all! Skyvern 2.0, scores state of the art 85.85% on WebVoyager Eval. View the full results here: https://eval.skyvern.com This is best-in-class performance of all WebAgents, giving advanced closed-source web agents like Google
This is best-in-class performance of all WebAgents, giving advanced closed-source web agents like Google Mariner a run for its money Achieving this SOTA result required expanding Skyvern’s original architecture from a single actor prompt to a planner-actor-validator agent loop. This acts as a supervisor function to confirm that the Task executor is achieving its objectives as expected, and report any errors / tweaks back to the Planner so it can make adjustments in real-time as needed
Or read this on Hacker News
