A Picture Is Worth a Graph: A Blueprint Debate Paradigm for Multimodal Reasoning
It addresses multimodal reasoning problems for AI systems, offering a novel method to improve debate-based reasoning, though it appears incremental as it builds on existing debate paradigms.
This paper tackles the challenges of opinion trivialization and distraction in multi-agent multimodal reasoning debates by proposing a deductive Blueprint Debate on Graphs (BDoG) approach, achieving state-of-the-art results on ScienceQA and MMBench benchmarks.
This paper presents a pilot study aimed at introducing multi-agent debate into multimodal reasoning. The study addresses two key challenges: the trivialization of opinions resulting from excessive summarization and the diversion of focus caused by distractor concepts introduced from images. These challenges stem from the inductive (bottom-up) nature of existing debating schemes. To address the issue, we propose a deductive (top-down) debating approach called Blueprint Debate on Graphs (BDoG). In BDoG, debates are confined to a blueprint graph to prevent opinion trivialization through world-level summarization. Moreover, by storing evidence in branches within the graph, BDoG mitigates distractions caused by frequent but irrelevant concepts. Extensive experiments validate that BDoG is able to achieve state-of-the-art results in ScienceQA and MMBench with significant improvements over previous methods. The source code can be accessed at https://github.com/thecharm/BDoG.