Metraipolis › archive › dc_ef4ad01cd625
VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal Agents — arXiv:2611.04894
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04894
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T21:40:15.539Z
- SHA-256 of the archived text
ef858b4fe613a9549dcb0576af5441e4095ba626c4bca01d78a970105ce9cd6b- Stable URL of this page
https://metraipolis.com/documento/dc_ef4ad01cd625
How to cite
VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal Agents — arXiv:2611.04894 — arXiv (en), https://arxiv.org/abs/2611.04894 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ef4ad01cd625 (Metraipolis archive dc_ef4ad01cd625, sha256 ef858b4fe613a9549dcb0576af5441e4095ba626c4bca01d78a970105ce9cd6b)
BibTeX
@misc{dcef4ad01cd625,
title = {VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal Agents — arXiv:2611.04894},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04894},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ef4ad01cd625; sha256 ef858b4fe613a9549dcb0576af5441e4095ba626c4bca01d78a970105ce9cd6b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04894. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multimodal agents use web and image tools to answer questions beyond their internal knowledge. Some search tasks use images mainly to identify an initial entity, then rely on text retrieval. These tasks offer limited insight into how agents connect information across images, objects, and search steps. We therefore focus on visual context management. This involves organizing and using visual information and linking it to other findings during search. Visually intensive tasks require agents to combine object appearance, local details, or spatial relations with external information. We introduce VisSearch-Bench, with 204 human-written tasks across 7 main domains and 25 subdomains. It covers Set-wise Visual Search, Sequential Visual Search, Hybrid Wide-Deep Search, Competitive Visual Disambiguation, and Visual-Structure-Guided Search. Each task provides a reference answer, traceable evidence, and scoring rules. Accuracy measures complete task success, while Process Score measures the correctness and completeness of individual results and subquestion answers. Across 16 multimodal models, the best system fully solves only 26.47% of tasks, even with search tools. These results highlight the challenge of linking visual evidence with search results to produce complete answers. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.04894 — 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 2026-11-04T21:35:49.696Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).