
HZ
Hongbo Zhang, Liuyang Song, Hang Zhou, Xinchen Liu, Wei He, Kai Han, Yunhe Wang
· 1 min read
ResearcharXiv cs.AI
VAHBench: A Harness Benchmark for Agentic Long-Video Generation
arXiv:2611.20535v1 Announce Type: new
Abstract: AI agents are commonly used for everyday information retrieval and coding. We ask whether they can also interpret human requests and turn them into complete videos. We introduce VAHBench, a benchmark that tests this ability through five short-drama briefs specifying story, characters, dialogue and duration. Agents plan and carry out production using shared generation tools. Evaluation combines video completeness and basic quality with checks of production reliability and reporting accuracy. Across 240 runs covering 48 configurations of general-purpose and video-specific agents, higher quality scores do not necessarily mean more complete delivery. Missing episodes, repeated footage and static filler reveal gaps between producing a video file and fulfilling the brief. Added composition tools help some agents but do not consistently improve performance. VAHBench measures how well agents translate user intent into finished video content and helps identify where that process breaks down.
Original source
This story was published by arXiv cs.AI and written by Hongbo Zhang, Liuyang Song, Hang Zhou, Xinchen Liu, Wei He, Kai Han, Yunhe Wang. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


