Metraipolis › archive › dc_149df5286c68
Faithful Chart Generation for Multimodal Deep Research: Frame-Evidence Co-Adaptation — arXiv:2610.00374
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.00374
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:09:05.756Z
- SHA-256 of the archived text
08f2c85330535b0b91195e07bdb9d7e569fc10a52cdd84665c6aefda7326e5de- Stable URL of this page
https://metraipolis.com/documento/dc_149df5286c68
How to cite
Faithful Chart Generation for Multimodal Deep Research: Frame-Evidence Co-Adaptation — arXiv:2610.00374 — arXiv (en), https://arxiv.org/abs/2610.00374 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_149df5286c68 (Metraipolis archive dc_149df5286c68, sha256 08f2c85330535b0b91195e07bdb9d7e569fc10a52cdd84665c6aefda7326e5de)
BibTeX
@misc{dc149df5286c68,
title = {Faithful Chart Generation for Multimodal Deep Research: Frame-Evidence Co-Adaptation — arXiv:2610.00374},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.00374},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_149df5286c68; sha256 08f2c85330535b0b91195e07bdb9d7e569fc10a52cdd84665c6aefda7326e5de},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00374. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Analytical charts in multimodal deep research encode quantitative claims, requiring every visualized value to be faithfully grounded in supporting evidence. Unlike retrieved images that mainly provide contextual information, charts require numerical fidelity: visualized values should not only match retrieved evidence quantitatively but also preserve its original meaning and scope. However, achieving such fidelity remains challenging because current systems usually construct visualization plans before knowing what quantitative evidence can actually be retrieved from the web. As a result, predefined plans may require entities, temporal ranges, or comparison dimensions that the retrieved evidence only partially supports. Existing approaches mainly address this issue through post-hoc verification after chart plans are fixed, enabling unsupported values to be identified but leaving the underlying visual frames unchanged. To address this challenge, we propose Frame-Evidence Co-Adaptation (FECA), an evidence-adaptive visual planning framework for multimodal deep research. Inspired by the bidirectional sensemaking process in Data-Frame Theory, FECA models chart generation as an iterative interaction between visual frames and retrieved evidence. Each visual frame is adaptive: the frame guides evidence acquisition, while retrieved evidence determines whether the frame should be accepted, revised, or dropped before rendering. By coupling visualization planning with evidence availability, FECA shifts chart generation from fixed-plan verification to adaptive evidence-grounded visual reasoning. Experiments on 100 real-world research topics show that FECA substantially improves numerical fidelity while preserving report quality and chart utility. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Human-Computer Interaction (cs.HC) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Graphics (cs.GR). Pagina del lavoro: https://arxiv.org/abs/2610.00374 — 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 2026-10-06T10:21:28.057Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).