arXiv：cs.CL· Khanh-Binh Nguyen, Van Dai Do, Tien Anh Nguyen, Svetha Venkatesh, Hung Le·· 13 小时前
DREAM：面向多模态多智能体辩论的动态分辨率分配
DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate
AI 导读
DREAM 通过动态分辨率分配与不确定性引导回滚聚合两项机制改进多模态多智能体辩论（MAD）。前者在一轮零样本探测中让智能体测试多种分辨率，用 Average Normalized Log-Likelihood（ANLL）量化不确定性并以自适应阈值分配各自最优分辨率；后者追踪各智能体多轮不确定性，恢复被群体压力推翻的早期低不确定性答案以抑制 groupthink。
正文
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.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.05615 [cs.AI] |
| (or arXiv:2610.05615v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.05615 arXiv-issued DOI via DataCite |
Submission history
From: Khanh-Binh Nguyen [view email]
[v1]
Sun, 4 Oct 2026 23:23:02 UTC (1,767 KB)
[v2]
Fri, 9 Oct 2026 03:24:46 UTC (1,767 KB)
来源：arXiv：cs.CL · arxiv.org