AgroNVILA: Perception-Reasoning Decoupling for Multi-view Agricultural Multimodal Large Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908887665344512 |
|---|---|
| author | Zhang, Jiarui Hu, Junqi Mai, Zurong Chen, Yuhang Lou, Shuohong Huang, Henglian Zhao, Lingyuan Huang, Jianxi Lu, Yutong Fu, Haohuan Zheng, Juepeng |
| author_facet | Zhang, Jiarui Hu, Junqi Mai, Zurong Chen, Yuhang Lou, Shuohong Huang, Henglian Zhao, Lingyuan Huang, Jianxi Lu, Yutong Fu, Haohuan Zheng, Juepeng |
| contents | Agricultural multimodal reasoning requires robust spatial understanding across varying scales, from ground-level close-ups to top-down UAV and satellite imagery. Existing Multi-modal Large Language Models (MLLMs) suffer from a significant "terrestrial-centric" bias, causing scale confusion and logic drift during complex agricultural planning. To address this, we introduce the first large-scale AgroOmni (288K), a multi-view training corpus designed to capture diverse spatial topologies and scales in modern precision agriculture. Built on this dataset, we propose AgroNVILA, an MLLM that utilizes a novel Perception-Reasoning Decoupling (PRD) architecture. On the perception side, we incorporate a View-Conditioned Meta-Net (VCMN), which injects macroscopic spatial context into visual tokens, resolving scale ambiguities with minimal computational overhead. On the reasoning side, Agriculture-aware Relative Policy Optimization (ARPO) leverages reinforcement learning to align the model's decision-making with expert agricultural logic, preventing statistical shortcuts. Extensive experiments demonstrate that AgroNVILA outperforms state-of-the-art MLLMs, achieving significant improvements (+15.18%) in multi-altitude agricultural reasoning, reflecting its robust capability for holistic agricultural spatial planning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_14342 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AgroNVILA: Perception-Reasoning Decoupling for Multi-view Agricultural Multimodal Large Language Models Zhang, Jiarui Hu, Junqi Mai, Zurong Chen, Yuhang Lou, Shuohong Huang, Henglian Zhao, Lingyuan Huang, Jianxi Lu, Yutong Fu, Haohuan Zheng, Juepeng Computer Vision and Pattern Recognition Artificial Intelligence Agricultural multimodal reasoning requires robust spatial understanding across varying scales, from ground-level close-ups to top-down UAV and satellite imagery. Existing Multi-modal Large Language Models (MLLMs) suffer from a significant "terrestrial-centric" bias, causing scale confusion and logic drift during complex agricultural planning. To address this, we introduce the first large-scale AgroOmni (288K), a multi-view training corpus designed to capture diverse spatial topologies and scales in modern precision agriculture. Built on this dataset, we propose AgroNVILA, an MLLM that utilizes a novel Perception-Reasoning Decoupling (PRD) architecture. On the perception side, we incorporate a View-Conditioned Meta-Net (VCMN), which injects macroscopic spatial context into visual tokens, resolving scale ambiguities with minimal computational overhead. On the reasoning side, Agriculture-aware Relative Policy Optimization (ARPO) leverages reinforcement learning to align the model's decision-making with expert agricultural logic, preventing statistical shortcuts. Extensive experiments demonstrate that AgroNVILA outperforms state-of-the-art MLLMs, achieving significant improvements (+15.18%) in multi-altitude agricultural reasoning, reflecting its robust capability for holistic agricultural spatial planning. |
| title | AgroNVILA: Perception-Reasoning Decoupling for Multi-view Agricultural Multimodal Large Language Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.14342 |