Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| 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 |