Metraipolis › archive › dc_fadeef5bba73

DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate — arXiv:2610.05615

Source: arXiv
Original: https://arxiv.org/abs/2610.05615
License (as archived): CC0-1.0
Archived: 2026-10-06T05:25:16.714Z
SHA-256 of the archived text: f971b79cbe8659c4f90432f957611f0b09048d96361c61856f38cd99f30f7613
Stable URL of this page: https://metraipolis.com/documento/dc_fadeef5bba73

How to cite

DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate — arXiv:2610.05615 — arXiv, https://arxiv.org/abs/2610.05615 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fadeef5bba73 (Metraipolis archive dc_fadeef5bba73, sha256 f971b79cbe8659c4f90432f957611f0b09048d96361c61856f38cd99f30f7613)

BibTeX

@misc{dcfadeef5bba73,
  title = {DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate — arXiv:2610.05615},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05615},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fadeef5bba73; sha256 f971b79cbe8659c4f90432f957611f0b09048d96361c61856f38cd99f30f7613},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05615. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multi-agent debate (MAD) has emerged as an effective paradigm to improve the reasoning capabilities of large language models (LLMs) and is increasingly being extended to multimodal settings. However, existing multimodal MAD frameworks typically expose agents to the same fixed visual input, ignoring substantial variation in the visual scale needed across samples and agents. In addition, these frameworks frequently suffer from groupthink, a phenomenon where agents prematurely abandon correct deductions to conform with confident but hallucinated peer responses. To address these bottlenecks, we introduce DREAM (Dynamic Resolution Assignment For Multimodal Multi-Agent Debate), which operates via two core components: (1) Dynamic Resolution Assignment, a zero-shot probe round where agents test multiple resolutions, quantify uncertainty using Average Normalized Log-Likelihood (ANLL), and use an adaptive threshold to assign each agent to its empirically optimal resolution; (2) Uncertainty-Guided Rollback Aggregation counters groupthink by tracking each agent's uncertainty over rounds and restoring early low-uncertainty answers overridden by group pressure. On six multimodal datasets, DREAM improves the accuracy-token trade-off over multi-agent debate baselines by 1.5-3.2% accuracy without dataset-specific tuning.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.05615 — 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 2026-10-06T05:24:05.612Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).