AgroNVILA: Perception-Reasoning Decoupling for Multi-view Agricultural Multimodal Large Language Models

TL;DR

AgroNVILA introduces a perception-reasoning decoupling framework with a large-scale multi-view dataset, significantly improving agricultural reasoning in multimodal large language models by addressing scale confusion and logic drift.

Contribution

The paper presents AgroNVILA, a novel multi-view agricultural multimodal large language model with a new dataset and architecture that enhances spatial understanding and reasoning in precision agriculture.

Findings

Achieved +15.18% improvement in multi-altitude agricultural reasoning.

Introduced AgroOmni, a large-scale multi-view dataset with 288K samples.

Demonstrated superior performance over state-of-the-art MLLMs in agricultural tasks.

Abstract

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.