Abstract
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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Nguyen, K. B., Do, V. D., Nguyen, T. A., Venkatesh, S., & Le, H. (2026). DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate. https://omanscience.com/en/articles/dream-dynamic-resolution-assignment-for-multimodal-multi-agent-debate
MLA 9
Nguyen, Khanh-Binh, et al. "DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate." https://omanscience.com/en/articles/dream-dynamic-resolution-assignment-for-multimodal-multi-agent-debate.
Chicago (author–date)
Nguyen, Khanh-Binh, Van Dai Do, Tien Anh Nguyen, Svetha Venkatesh, and Hung Le. 2026. "DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate." https://omanscience.com/en/articles/dream-dynamic-resolution-assignment-for-multimodal-multi-agent-debate.
Harvard
Nguyen, K. B., Do, V. D., Nguyen, T. A., Venkatesh, S. and Le, H. (2026) 'DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate', Available at: https://omanscience.com/en/articles/dream-dynamic-resolution-assignment-for-multimodal-multi-agent-debate.
Vancouver
Nguyen KB, Do VD, Nguyen TA, Venkatesh S, Le H. DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate. https://omanscience.com/en/articles/dream-dynamic-resolution-assignment-for-multimodal-multi-agent-debate
IEEE
K. B. Nguyen, V. D. Do, T. A. Nguyen, S. Venkatesh, and H. Le, "DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate," https://omanscience.com/en/articles/dream-dynamic-resolution-assignment-for-multimodal-multi-agent-debate.