mlsanityData to 7 Oct 2026

A Picture Is Worth a Graph: A Blueprint Debate Paradigm for Multimodal Reasoning

arXiv 2403.14972 ↗First posted 22 Mar 2024cs.AI cs.CL cs.MAcited by 11

On the map: LLM reasoning → Multimodal reasoning

also in 1 more
Abstract (arXiv)

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.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 19 of its 43 references that are in the map. First posted on arXiv 22 Mar 2024.

Builds on

19 of 43 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning23 Jan
  2. 2023Compositional Chain-of-Thought Prompting for Large Multimodal Models27 Nov
  3. 2023MMBench: Is Your Multi-modal Model an All-around Player?12 Jul
  4. 2023T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Mixed Large Language Model Signals for Science Question Answering5 May
  5. 2023Multimodal Chain-of-Thought Reasoning in Language Models2 Feb

Other references · 14

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  4. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,855
  5. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
  6. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  7. 2015Microsoft COCO Captions: Data Collection and Evaluation Servercited by 1,447
  8. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 995
  9. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 810
  10. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 704
  11. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 221
  12. 2023Progressive-Hint Prompting Improves Reasoning in Large Language Modelscited by 147
2 more
  1. 2023Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answeringcited by 97
  2. 2023SCITUNE: Aligning Large Language Models with Human-Curated Scientific Multimodal Instructionscited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 6.

11 papers.

  1. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 176
  2. 2025Removal of Hallucination on Hallucination: Debate-Augmented RAGcited by 29
  3. 2025RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigmcited by 7
  4. 2025Harnessing Chain-of-Thought Reasoning in Multimodal Large Language Models for Face Anti-Spoofingcited by 5
  5. 2026Mol-Debate: Multi-Agent Debate Improves Structural Reasoning in Molecular Designcited by 1
  6. 2025Rationale-Enhanced Decoding for Multi-modal Chain-of-Thoughtcited by 0
  7. 2026DeAR: Decentralized Agentic Reasoning via Capability Grounding and Collaborative Thought Navigationcited by 0
  8. 2026ORBITER: Conflict-Aware Decision-Making for Agentic Last-Mile Deliverycited by 0
  9. 2026Meta-Moderator: Empowering Multi-Agent Debate with Meta-Cognitioncited by 0
  10. 2026Molecular LLM Agents: From Architectural Design to Scientific Autonomycited by 0
  11. 2026CDPR: Counterfactual Advantage-based Credit Assignment for Cost-Aware Sequential Medical Diagnosiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning
  2. 2025Debating for Better Reasoning: An Unsupervised Multimodal Approach
  3. 2026Multimodal Collaborative Debate for Zero-Shot Time Series Reasoning
  4. 2025WISE: Weighted Iterative Society-of-Experts for Robust Multimodal Multi-Agent Debate
  5. 2026M3MAD-Bench: Multi-Dimensional Evaluation of Multi-Agent Debate Across Domains and Modalities
  6. 2026The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning
  7. 2026MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory
  8. 2026ICDAR2026 Competition on Multimodal Reasoning over Documents in Multiple Domains