Agri-R1: Agricultural Reasoning for Disease Diagnosis via Automated-Synthesis and Reinforcement Learning

TL;DR

Agri-R1 introduces a reasoning-enhanced large model for agricultural disease diagnosis that leverages automated reasoning data synthesis and reinforcement learning, achieving high performance with limited labeled data.

Contribution

The paper presents a novel framework combining automated reasoning data generation and RL training with domain-specific rewards for agriculture-related vision-language tasks.

Findings

Achieved 27.9% relative gain in disease recognition accuracy.

Improved agricultural knowledge QA by 33.3%.

Enhanced cross-domain generalization by 26.10 points.

Abstract

Agricultural disease diagnosis challenges VLMs, as conventional fine-tuning requires extensive labels, lacks interpretability, and generalizes poorly. While reasoning improves model robustness, existing methods rely on costly expert annotations and rarely address the open-ended, diverse nature of agricultural queries. To address these limitations, we propose \textbf{Agri-R1}, a reasoning-enhanced large model for agriculture. Our framework automates high-quality reasoning data generation via vision-language synthesis and LLM-based filtering, using only 19\% of available samples. Training employs Group Relative Policy Optimization (GRPO) with a novel reward function that integrates domain-specific lexicons and fuzzy matching to assess both correctness and linguistic flexibility in open-ended responses. Evaluated on CDDMBench, our resulting 3B-parameter model achieves performance competitive with 7B- to 13B-parameter baselines, showing a +27.9\% relative gain in disease recognition accuracy, +33.3\% in agricultural knowledge QA, and a +26.10-point improvement in cross-domain generalization over standard fine-tuning. These results suggest that automated reasoning synthesis paired with domain-aware reward design may provide a broadly applicable paradigm for RL-based VLM adaptation in data-scarce specialized domains. Our code and data are publicly available at: https://github.com/CPJ-Agricultural/Agri-R1.