Metraipolis › archive › dc_f6cbd59bd92a
MetaVideoAgent: Automated Video-Agent Evolution for Long-Form Video Understanding — arXiv:2608.04587
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04587
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:48:00.240Z
- SHA-256 of the archived text
b0733fbe766eb4563405a5ff0230bf8fa26ce37df6826fdb094642f344519ac2- Stable URL of this page
https://metraipolis.com/documento/dc_f6cbd59bd92a
How to cite
MetaVideoAgent: Automated Video-Agent Evolution for Long-Form Video Understanding — arXiv:2608.04587 — arXiv (en), https://arxiv.org/abs/2608.04587 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f6cbd59bd92a (Metraipolis archive dc_f6cbd59bd92a, sha256 b0733fbe766eb4563405a5ff0230bf8fa26ce37df6826fdb094642f344519ac2)
BibTeX
@misc{dcf6cbd59bd92a,
title = {MetaVideoAgent: Automated Video-Agent Evolution for Long-Form Video Understanding — arXiv:2608.04587},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04587},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f6cbd59bd92a; sha256 b0733fbe766eb4563405a5ff0230bf8fa26ce37df6826fdb094642f344519ac2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04587. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-form video understanding requires locating sparse, question-relevant evidence in long, multimodal videos. Real-world video distributions differ in modality-specific information density, content structure, and evidence patterns, causing fixed video-agent designs to incur redundant processing or fail when mismatched. Extending automated agent evolution from text to video is challenging because full long-video execution makes candidate validation expensive, failures propagate across coupled evidence-processing stages, and complex preprocessing, perception tools, and localization strategies make code-level updates difficult to implement reliably. We introduce MetaVideoAgent, a framework that automatically evolves a video agent for a target distribution. It profiles information density and evidence requirements from sparsely sampled frames and associated queries to guide initial design, then compresses localized failures into independently executable minimal validation tasks. It constructs evidence-grounded Gold Paths, audits Student trajectories, aggregates recurring failures across samples, and attributes them to responsible modules. A modular agent representation constrains each update to the primary responsible module and its necessary dependencies. We further introduce VA-EvoBench, covering eight video distributions with separate evolution and held-out splits. With four evolution iterations per distribution, MetaVideoAgent improves every initial agent and raises macro-average accuracy from 38.44% to 51.47%, at an average evolution cost of 3.54M tokens per distribution. The evolved agents outperform the strongest prior fixed-design video agent by 6.39 percentage points while using the fewest tokens and video frames per question among the compared video agents. We will release all code and data to support reproducible research. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-06 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.04587 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-31T11:37:40.688Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).