Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.20085 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908689930125312 |
|---|---|
| author | Wang, Chujie Luo, Zhiyuan Liu, Ruiqi Ran, Can Fan, Shenghua Chen, Xi He, Chu |
| author_facet | Wang, Chujie Luo, Zhiyuan Liu, Ruiqi Ran, Can Fan, Shenghua Chen, Xi He, Chu |
| contents | The current remote sensing image analysis task is increasingly evolving from traditional object recognition to complex intelligence reasoning, which places higher requirements on the model's reasoning ability and the flexibility of tool invocation. To this end, we propose a new multimodal agent framework, Vision-Interleaved Chain-of-Thought Framework (VICoT), which implements explicit multi-round reasoning by dynamically incorporating visual tools into the chain of thought. Through a stack-based reasoning structure and a modular MCP-compatible tool suite, VICoT enables LLMs to efficiently perform multi-round, interleaved vision-language reasoning tasks with strong generalization and flexibility.We also propose the Reasoning Stack distillation method to migrate complex Agent behaviors to small, lightweight models, which ensures the reasoning capability while significantly reducing complexity. Experiments on multiple remote sensing benchmarks demonstrate that VICoT significantly outperforms existing SOTA frameworks in reasoning transparency, execution efficiency, and generation quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_20085 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | VICoT-Agent: A Vision-Interleaved Chain-of-Thought Framework for Interpretable Multimodal Reasoning and Scalable Remote Sensing Analysis Wang, Chujie Luo, Zhiyuan Liu, Ruiqi Ran, Can Fan, Shenghua Chen, Xi He, Chu Artificial Intelligence Multiagent Systems The current remote sensing image analysis task is increasingly evolving from traditional object recognition to complex intelligence reasoning, which places higher requirements on the model's reasoning ability and the flexibility of tool invocation. To this end, we propose a new multimodal agent framework, Vision-Interleaved Chain-of-Thought Framework (VICoT), which implements explicit multi-round reasoning by dynamically incorporating visual tools into the chain of thought. Through a stack-based reasoning structure and a modular MCP-compatible tool suite, VICoT enables LLMs to efficiently perform multi-round, interleaved vision-language reasoning tasks with strong generalization and flexibility.We also propose the Reasoning Stack distillation method to migrate complex Agent behaviors to small, lightweight models, which ensures the reasoning capability while significantly reducing complexity. Experiments on multiple remote sensing benchmarks demonstrate that VICoT significantly outperforms existing SOTA frameworks in reasoning transparency, execution efficiency, and generation quality. |
| title | VICoT-Agent: A Vision-Interleaved Chain-of-Thought Framework for Interpretable Multimodal Reasoning and Scalable Remote Sensing Analysis |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2511.20085 |