Metraipolis › archive › dc_4673bed55102
Can Agents Win the Video Browser Showdown? — arXiv:2609.07311
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.07311
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:31:42.402Z
- SHA-256 of the archived text
abb7d6a0753fe8a2391c3e062285570d90d8197b0746f783bcfd78c834e7d7b5- Stable URL of this page
https://metraipolis.com/documento/dc_4673bed55102
How to cite
Can Agents Win the Video Browser Showdown? — arXiv:2609.07311 — arXiv (en), https://arxiv.org/abs/2609.07311 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4673bed55102 (Metraipolis archive dc_4673bed55102, sha256 abb7d6a0753fe8a2391c3e062285570d90d8197b0746f783bcfd78c834e7d7b5)
BibTeX
@misc{dc4673bed55102,
title = {Can Agents Win the Video Browser Showdown? — arXiv:2609.07311},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.07311},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4673bed55102; sha256 abb7d6a0753fe8a2391c3e062285570d90d8197b0746f783bcfd78c834e7d7b5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07311. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Searching large video collections is typically an interactive process in which users play two roles. First, they hold the search intent: the underlying goal that determines what content they seek and why. Second, users must operationalize this intent through an iterative search loop. Users translate their intent into queries, browse the retrieved candidates, and refine their queries based on the results. In this paper, we investigate the capabilities of modern Vision Language Models (VLM) and agentic approaches to reach search goals interactively and fully autonomously. Specifically, we study whether a provided initial specification of a search goal might be sufficient to solve traditionally interactive search tasks with an agentic system. Provided that the involved VLMs are not aware of the whole large video dataset in advance, the key challenge lies in the effective combination of an existing interactive video search system and a smart VLM agent controlling the system. While the search system provides indexing and efficient querying, the VLM-based agents analyze top-ranked items and make decisions about next actions. Our results show that modern agents can autonomously operate interactive video retrieval systems to solve many search tasks from an initial intent description, achieving performance competitive with strong historical expert-operated systems in several settings. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.MM). Categorie arXiv: Multimedia (cs.MM). Pagina del lavoro: https://arxiv.org/abs/2609.07311 — 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 2026-10-16T15:14:52.504Z dalla pagina https://arxiv.org/catchup/cs.MM/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).