CutVerse: A Compositional GUI Agents Benchmark for Media Post-Production Editing
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913144753881088 |
|---|---|
| author | Hu, Haobo Guo, Xiangwu Chen, Zhiheng Gao, Difei Liu, Haotian Jin, Libiao Mao, Qi |
| author_facet | Hu, Haobo Guo, Xiangwu Chen, Zhiheng Gao, Difei Liu, Haotian Jin, Libiao Mao, Qi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_19484 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CutVerse: A Compositional GUI Agents Benchmark for Media Post-Production Editing Hu, Haobo Guo, Xiangwu Chen, Zhiheng Gao, Difei Liu, Haotian Jin, Libiao Mao, Qi Computer Vision and Pattern Recognition Artificial Intelligence Graphics Human-Computer Interaction 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. |
| title | CutVerse: A Compositional GUI Agents Benchmark for Media Post-Production Editing |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Graphics Human-Computer Interaction |
| url | https://arxiv.org/abs/2605.19484 |