OpenApps: Simulating Environment Variations to Measure UI Agent Reliability

ICLROral2026

Authors: Karen Ullrich, Jingtong Su, Claudia Shi, Arjun Subramonian, Amir Bar, Ivan Evtimov, Nikolaos Tsilivis, Randall Balestriero, Julia Kempe, Mark Ibrahim
Affiliation: Meta AI
Venue: ICLR 2026
Track: Oral

TL;DR

We introduce a new environment, OpenApps, for generating thousands of versions of apps to test UI agent reliability.

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

agent

← All ICLR 2026 Oral papers · Browse the whole archive