Metraipolis › archive › dc_09d90e1f3e27
Wyvern: An Agentic Framework for Generating Grounded Multimodal Reports — arXiv:2608.14446
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.14446
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T02:20:50.254Z
- SHA-256 of the archived text
726e9995773c8cdd225fcabe076c6b5989410fd28b6c0e01f2bc20f2cce331e8- Stable URL of this page
https://metraipolis.com/documento/dc_09d90e1f3e27
How to cite
Wyvern: An Agentic Framework for Generating Grounded Multimodal Reports — arXiv:2608.14446 — arXiv (en), https://arxiv.org/abs/2608.14446 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09d90e1f3e27 (Metraipolis archive dc_09d90e1f3e27, sha256 726e9995773c8cdd225fcabe076c6b5989410fd28b6c0e01f2bc20f2cce331e8)
BibTeX
@misc{dc09d90e1f3e27,
title = {Wyvern: An Agentic Framework for Generating Grounded Multimodal Reports — arXiv:2608.14446},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.14446},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09d90e1f3e27; sha256 726e9995773c8cdd225fcabe076c6b5989410fd28b6c0e01f2bc20f2cce331e8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14446. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In the current artificial intelligence-driven innovation era, the pace of knowledge growth is accelerating, and is hard to keep up with. While generative models are increasingly used to synthesize content, they often lack in information grounding. To address these peculiarities of our time, we propose Wyvern, a multi-agent framework for the automated generation of grounded, multimodal technical reports. Wyvern allows for the generation of multimodal outputs, integrating images, tables, and text with supporting references in a unified report. Additionally, a particular focus is placed on the grounding of the content, with the implementation of a claims auto-revision stage. We conduct a human evaluation study to assess the quality of our proposed framework. The results show that the figures' informativeness is perceived as superior to that of a recent baseline in 87% of cases. Furthermore, Wyvern's reports are rated as more useful than those produced by three alternative methods in 63% to 100% of instances. We also carry out automatic evaluations showing that Wyvern gains up to 2.3$\times$ in citation recall and 1.6$\times$ in citation precision with respect to the baselines. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.14446 — 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 2026-10-19T02:02:02.823Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).