Metraipolis › archive › dc_0d2fdbb6bd83
Multi-Agent Discovery and Resource-Aware Autonomous Exploration of Scientific Datasets — arXiv:2608.22045
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.22045
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:42:34.261Z
- SHA-256 of the archived text
ff8e063fef591b4a108845ce91a3318a35719ee402a7c884fe7c257a39fae609- Stable URL of this page
https://metraipolis.com/documento/dc_0d2fdbb6bd83
How to cite
Multi-Agent Discovery and Resource-Aware Autonomous Exploration of Scientific Datasets — arXiv:2608.22045 — arXiv (en), https://arxiv.org/abs/2608.22045 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0d2fdbb6bd83 (Metraipolis archive dc_0d2fdbb6bd83, sha256 ff8e063fef591b4a108845ce91a3318a35719ee402a7c884fe7c257a39fae609)
BibTeX
@misc{dc0d2fdbb6bd83,
title = {Multi-Agent Discovery and Resource-Aware Autonomous Exploration of Scientific Datasets — arXiv:2608.22045},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.22045},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0d2fdbb6bd83; sha256 ff8e063fef591b4a108845ce91a3318a35719ee402a7c884fe7c257a39fae609},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22045. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Modern scientific facilities and instruments generate datasets at scales that are difficult for individual researchers to discover, access, and explore. Although many datasets are publicly available, using them often requires familiarity with repository organization, data formats, multiresolution structures, and visualization parameters. We present WebVisus, a constrained and resource-aware multi-agent system for discovering and autonomously exploring remote, multiresolution scientific datasets. Given a natural-language research question, WebVisus identifies the user's intent and launches an autonomous exploration agent that examines slices, volumes, and timesteps while adapting data resolution and retrieval quality to available client memory and computational resources. This design supports progressive exploration without complete dataset downloads or manual configuration of low-level visualization parameters using natural languages. We report the system architecture, constrained agent protocol, resource-aware access mechanism, and case studies evaluating autonomous visual exploration and resource-aware agentic access across scientific datasets. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI). Categorie arXiv: Human-Computer Interaction (cs.HC) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.22045 — 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 2026-10-18T07:37:52.847Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).