ScreenSpot-v-2

The 'ScreenSpot-v-2' dataset/benchmark contains a collection of screenshots used to evaluate the performance of mobile device control agents in solving complex tasks that require long-horizon planning and precise operations.

Papers using ScreenSpot-v-2 (3)

K^2-Agent: Co-Evolving Know-What and Know-How for Hierarchical Mobile Device Control2026Hi-Agent: Hierarchical Vision-Language Agents for Mobile Device Control2025UI-AGILE: Advancing GUI Agents with Effective Reinforcement Learning and Precise Inference-Time Grounding2025