Metraipolis › archive › dc_eb5ff209ba18

AttriSwarm: Orchestrating Agent Swarms for Cross-Page Visual Attribution — arXiv:2611.04504

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04504
License (as archived)
CC0-1.0
Archived
2026-11-04T12:00:55.223Z
SHA-256 of the archived text
4b9a1000982a18773bb49f7cc37dbbc1affbe90c383370f443518b59ddd457c0
Stable URL of this page
https://metraipolis.com/documento/dc_eb5ff209ba18

How to cite

AttriSwarm: Orchestrating Agent Swarms for Cross-Page Visual Attribution — arXiv:2611.04504 — arXiv (en), https://arxiv.org/abs/2611.04504 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb5ff209ba18 (Metraipolis archive dc_eb5ff209ba18, sha256 4b9a1000982a18773bb49f7cc37dbbc1affbe90c383370f443518b59ddd457c0)
BibTeX
@misc{dceb5ff209ba18,
  title = {AttriSwarm: Orchestrating Agent Swarms for Cross-Page Visual Attribution — arXiv:2611.04504},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04504},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb5ff209ba18; sha256 4b9a1000982a18773bb49f7cc37dbbc1affbe90c383370f443518b59ddd457c0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04504. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal large language models (MLLMs) increasingly address knowledge-intensive tasks by integrating evidence scattered across multiple document pages into a final answer. Because such answers are synthesized from many pages, the link between the answer and its supporting visual evidence can become obscured, hindering verification and trust. Cross-page visual attribution is therefore essential: it requires identifying the supporting pages and localizing fine-grained evidence regions within them, thereby making multi-page reasoning transparent and auditable. Existing approaches either process multiple pages jointly or iteratively refine evidence within a single trajectory, risking cross-page context pollution and, for interactive methods, substantial sequential overhead. We introduce \textbf{AttriSwarm}, an agent-swarm framework that assigns these concerns to separate roles: a leader handles global cross-page reasoning, while subagents perform page-wise attribution in isolation and in parallel. To support training and evaluation, we construct \textbf{AttriDoc}, a cross-page QA dataset linking supporting pages to their annotated evidence regions, and use it for role-specific training of AttriSwarm, improving answer accuracy, page-level $F_1$, and region-level IoU over its training-free counterpart by an average of 18.94, 29.34, and 23.04 percentage points, respectively, across three open-source backbones and three datasets.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2611.04504 — 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 2026-11-04T12:00:55.072Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).