Agri-R1: Agricultural Reasoning for Disease Diagnosis via Automated-Synthesis and Reinforcement Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914465559085056 |
|---|---|
| author | Zhang, Wentao Xu, Mingkun Zhang, Qi Li, Shangyang Wong, Derek F. Wang, Lifei Yang, Yanchao Lu, Lina Fang, Tao |
| author_facet | Zhang, Wentao Xu, Mingkun Zhang, Qi Li, Shangyang Wong, Derek F. Wang, Lifei Yang, Yanchao Lu, Lina Fang, Tao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_04672 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Agri-R1: Agricultural Reasoning for Disease Diagnosis via Automated-Synthesis and Reinforcement Learning Zhang, Wentao Xu, Mingkun Zhang, Qi Li, Shangyang Wong, Derek F. Wang, Lifei Yang, Yanchao Lu, Lina Fang, Tao Computer Vision and Pattern Recognition Computation and Language 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. |
| title | Agri-R1: Agricultural Reasoning for Disease Diagnosis via Automated-Synthesis and Reinforcement Learning |
| topic | Computer Vision and Pattern Recognition Computation and Language |
| url | https://arxiv.org/abs/2601.04672 |