Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Jusheng, Fan, Yijia, Lin, Wenjun, Chen, Ruiqi, Jiang, Haoyi, Chai, Wenhao, Wang, Jian, Wang, Keze
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.23399
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915312551591936
author Zhang, Jusheng
Fan, Yijia
Lin, Wenjun
Chen, Ruiqi
Jiang, Haoyi
Chai, Wenhao
Wang, Jian
Wang, Keze
author_facet Zhang, Jusheng
Fan, Yijia
Lin, Wenjun
Chen, Ruiqi
Jiang, Haoyi
Chai, Wenhao
Wang, Jian
Wang, Keze
contents We propose GAM-Agent, a game-theoretic multi-agent framework for enhancing vision-language reasoning. Unlike prior single-agent or monolithic models, GAM-Agent formulates the reasoning process as a non-zero-sum game between base agents--each specializing in visual perception subtasks--and a critical agent that verifies logic consistency and factual correctness. Agents communicate via structured claims, evidence, and uncertainty estimates. The framework introduces an uncertainty-aware controller to dynamically adjust agent collaboration, triggering multi-round debates when disagreement or ambiguity is detected. This process yields more robust and interpretable predictions. Experiments on four challenging benchmarks--MMMU, MMBench, MVBench, and V*Bench--demonstrate that GAM-Agent significantly improves performance across various VLM backbones. Notably, GAM-Agent boosts the accuracy of small-to-mid scale models (e.g., Qwen2.5-VL-7B, InternVL3-14B) by 5--6\%, and still enhances strong models like GPT-4o by up to 2--3\%. Our approach is modular, scalable, and generalizable, offering a path toward reliable and explainable multi-agent multimodal reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2505_23399
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning
Zhang, Jusheng
Fan, Yijia
Lin, Wenjun
Chen, Ruiqi
Jiang, Haoyi
Chai, Wenhao
Wang, Jian
Wang, Keze
Artificial Intelligence
We propose GAM-Agent, a game-theoretic multi-agent framework for enhancing vision-language reasoning. Unlike prior single-agent or monolithic models, GAM-Agent formulates the reasoning process as a non-zero-sum game between base agents--each specializing in visual perception subtasks--and a critical agent that verifies logic consistency and factual correctness. Agents communicate via structured claims, evidence, and uncertainty estimates. The framework introduces an uncertainty-aware controller to dynamically adjust agent collaboration, triggering multi-round debates when disagreement or ambiguity is detected. This process yields more robust and interpretable predictions. Experiments on four challenging benchmarks--MMMU, MMBench, MVBench, and V*Bench--demonstrate that GAM-Agent significantly improves performance across various VLM backbones. Notably, GAM-Agent boosts the accuracy of small-to-mid scale models (e.g., Qwen2.5-VL-7B, InternVL3-14B) by 5--6\%, and still enhances strong models like GPT-4o by up to 2--3\%. Our approach is modular, scalable, and generalizable, offering a path toward reliable and explainable multi-agent multimodal reasoning.
title GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning
topic Artificial Intelligence
url https://arxiv.org/abs/2505.23399