MARIC: Multi-Agent Reasoning for Image Classification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914045593911296 |
|---|---|
| author | Seo, Wonduk Yu, Minhyeong An, Hyunjin Lee, Seunghyun |
| author_facet | Seo, Wonduk Yu, Minhyeong An, Hyunjin Lee, Seunghyun |
| contents | Image classification has traditionally relied on parameter-intensive model training, requiring large-scale annotated datasets and extensive fine tuning to achieve competitive performance. While recent vision language models (VLMs) alleviate some of these constraints, they remain limited by their reliance on single pass representations, often failing to capture complementary aspects of visual content. In this paper, we introduce Multi Agent based Reasoning for Image Classification (MARIC), a multi agent framework that reformulates image classification as a collaborative reasoning process. MARIC first utilizes an Outliner Agent to analyze the global theme of the image and generate targeted prompts. Based on these prompts, three Aspect Agents extract fine grained descriptions along distinct visual dimensions. Finally, a Reasoning Agent synthesizes these complementary outputs through integrated reflection step, producing a unified representation for classification. By explicitly decomposing the task into multiple perspectives and encouraging reflective synthesis, MARIC mitigates the shortcomings of both parameter-heavy training and monolithic VLM reasoning. Experiments on 4 diverse image classification benchmark datasets demonstrate that MARIC significantly outperforms baselines, highlighting the effectiveness of multi-agent visual reasoning for robust and interpretable image classification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_14860 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MARIC: Multi-Agent Reasoning for Image Classification Seo, Wonduk Yu, Minhyeong An, Hyunjin Lee, Seunghyun Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Multiagent Systems Image classification has traditionally relied on parameter-intensive model training, requiring large-scale annotated datasets and extensive fine tuning to achieve competitive performance. While recent vision language models (VLMs) alleviate some of these constraints, they remain limited by their reliance on single pass representations, often failing to capture complementary aspects of visual content. In this paper, we introduce Multi Agent based Reasoning for Image Classification (MARIC), a multi agent framework that reformulates image classification as a collaborative reasoning process. MARIC first utilizes an Outliner Agent to analyze the global theme of the image and generate targeted prompts. Based on these prompts, three Aspect Agents extract fine grained descriptions along distinct visual dimensions. Finally, a Reasoning Agent synthesizes these complementary outputs through integrated reflection step, producing a unified representation for classification. By explicitly decomposing the task into multiple perspectives and encouraging reflective synthesis, MARIC mitigates the shortcomings of both parameter-heavy training and monolithic VLM reasoning. Experiments on 4 diverse image classification benchmark datasets demonstrate that MARIC significantly outperforms baselines, highlighting the effectiveness of multi-agent visual reasoning for robust and interpretable image classification. |
| title | MARIC: Multi-Agent Reasoning for Image Classification |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Multiagent Systems |
| url | https://arxiv.org/abs/2509.14860 |