CutVerse: A Compositional GUI Agents Benchmark for Media Post-Production Editing
For researchers developing GUI agents, this benchmark reveals a significant performance gap in professional creative workflows, indicating that current agents are insufficient for realistic media editing tasks.
CutVerse benchmarks GUI agents on 186 complex, long-horizon media post-production tasks across 7 professional applications, finding that existing agents achieve only 36.0% task success, highlighting challenges in domain-specific planning and reliability.
While GUI agents have made significant progress in web navigation and basic operating system tasks, their capabilities in professional creative workflows remain largely underexplored. To bridge this gap, we introduce Cutverse, a benchmark designed to systematically evaluate autonomous GUI agents in realistic media post-production environments. We curate expert demonstrations across 7 professional applications (e.g., Premiere Pro, Photoshop), covering 186 complex, long-horizon tasks grounded in authentic editing workflows, involving dense multimodal interfaces and tightly coupled interaction sequences. To support scalable evaluation, we develop a lightweight parser that transforms raw screen recordings and low-level interaction logs into structured, compositional GUI action trajectories with precise grounding. Extensive evaluations reveal that existing agents achieve only 36.0\% task success on realistic media editing tasks, underscoring the challenges posed by complex, long-horizon media post-production workflows in our benchmark.While current models demonstrate promising spatial grounding, multimodal alignment, and coordinated action execution, they remain limited in long-horizon reliability and domain-specific planning.