Back to search

Georgia Institute of Technology

Multiagent debate among vision-language models improves multimodal reasoning

Abstract

dc:description.abstract

We propose a framework for improving the multimodal reasoning capabilities of vision-language models through multiagent debate, where multiple models engage in a structured debate process, taking opposing perspectives and exchanging arguments about a given multimodal input containing text and images. Through this iterative debate, the models can complement each other's strengths, surface relevant evidence across modalities, and arrive at more robust and well-reasoned conclusions compared to using a single model. Evaluated on the ScienceQA dataset, models involved in a debate significantly outperformed their individual baselines, with prompting strategies resulting in further improvement. The debate process allows models to identify flaws, provide additional evidence, and negotiate stronger final answers by combining diverse skills, highlighting the potential of constructive disagreement and debate for overcoming limitations in current multimodal AI systems.

Degree

thesis:*
Level thesis:degree_level
Masters
Department dc:contributor.department
Computer Science
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Murugappan, Ganesh Meyyappan
Advisor dc:contributor.advisor
  • Zhang, Chao
Committee members dc:contributor.committeemember
  • Zhao, Tuo
  • Kira, Zsolt

Subjects

dc:subject × 3

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1853/75282

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Murugappan, Ganesh Meyyappan. Multiagent debate among vision-language models improves multimodal reasoning. Masters thesis, Georgia Institute of Technology, 2024. https://hdl.handle.net/1853/75282