Toolsslug: arenawebdevpreferences

ArenaWebdevPreferences

Open agent trace dataset from Arena for preference evaluation research in web development.

Curated Intelligence

1 items · Page 1/1
Arena.ai (@arena)T1·Agents
62 pts
Arena Open-Sources Agent Interaction Evaluation Datasets

Arena.ai introduces Interaction-as-a-Judge, an evaluation paradigm in which computer-use agents directly play games and operate apps to judge quality, improving alignment with user preferences, error detection, and downstream generation. The team also open-sources two agent trace datasets, ArenaWebdevPreferences and ArenaWebdevCorrectness, to support future research.