From UAV Imagery to Agronomic Reasoning: A Multimodal LLM Benchmark for Plant Phenotyping

• URL: http://arxiv.org/abs/2604.09907v1
• Date: Fri, 10 Apr 2026 21:08:18 GMT
• Title: From UAV Imagery to Agronomic Reasoning: A Multimodal LLM Benchmark for Plant Phenotyping
• Abstract summary: PlantXpert is an evidence-grounded multimodal reasoning benchmark for soybean and cotton phenotyping.<n>We constructed a dataset comprising 385 digital images and more than 3,000 benchmark samples spanning key plant science domains.<n>The results indicate that task-specific fine-tuning leads to substantial improvement in accuracy, with models such as Qwen3-VL-4B and Qwen3-VL-30B achieving up to 78%.
• Score: 11.924426769227829
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: To improve crop genetics, high-throughput, effective and comprehensive phenotyping is a critical prerequisite. While such tasks were traditionally performed manually, recent advances in multimodal foundation models, especially in vision-language models (VLMs), have enabled more automated and robust phenotypic analysis. However, plant science remains a particularly challenging domain for foundation models because it requires domain-specific knowledge, fine-grained visual interpretation, and complex biological and agronomic reasoning. To address this gap, we develop PlantXpert, an evidence-grounded multimodal reasoning benchmark for soybean and cotton phenotyping. Our benchmark provides a structured and reproducible framework for agronomic adaptation of VLMs, and enables controlled comparison between base models and their domain-adapted counterparts. We constructed a dataset comprising 385 digital images and more than 3,000 benchmark samples spanning key plant science domains including disease, pest control, weed management, and yield. The benchmark can assess diverse capabilities including visual expertise, quantitative reasoning, and multi-step agronomic reasoning. A total of 11 state-of-the-art VLMs were evaluated. The results indicate that task-specific fine-tuning leads to substantial improvement in accuracy, with models such as Qwen3-VL-4B and Qwen3-VL-30B achieving up to 78%. At the same time, gains from model scaling diminish beyond a certain capacity, generalization across soybean and cotton remains uneven, and quantitative as well as biologically grounded reasoning continue to pose substantial challenges. These findings suggest that PlantXpert can serve as a foundation for assessing evidence-grounded agronomic reasoning and for advancing multimodal model development in plant science.

Related papers

• MHE-Former: Multi-Hypothesis Transformers via Entropy Maximization for 3D Mesh Recovery [80.22216005340283]
  We introduce an exploration--exploitation paradigm for ambiguous mesh recovery with multi-hypothesis learning and selection.<n>During exploitation, we propose Hypothesis Selection, a context-aware process for multiple predictions.<n>Our framework achieves state-of-the-art performance in accuracy and diversity across multiple datasets.
  arXiv  Detail & Related papers  (2026-09-09T18:39:03Z)
• ViroBench: Benchmarking Nucleotide Foundation Models on Viral Genomics Tasks [86.89727311669937]
  We introduce ViroBench, the first comprehensive and large-scale benchmark specifically designed for nucleotide foundation models (NFMs)<n>ViroBench evaluates models across two critical dimensions: biological understanding and latent biosecurity risk, covering 18 diverse scenarios within 4 task types.<n>ViroBench provides interpretable, diagnostic evaluations and a reproducible measurement framework for future research on viral nucleotide foundation models.
  arXiv  Detail & Related papers  (2026-05-25T03:31:46Z)
• AgriPath: A Systematic Exploration of Architectural Trade-offs for Crop Disease Classification [45.52399819498234]
  This work presents a systematic empirical comparison of three model paradigms for fine-grained crop disease classification.<n>We introduce AgriPath-LF16, a benchmark containing 111k images spanning 16 crops and 41 diseases.<n>CNNs achieve the highest accuracy on lab imagery but degrade under domain shift.<n> Contrastive VLMs provide a robust and parameter-efficient alternative with competitive cross-domain performance.
  arXiv  Detail & Related papers  (2026-03-08T17:28:01Z)
• LeafNet: A Large-Scale Dataset and Comprehensive Benchmark for Foundational Vision-Language Understanding of Plant Diseases [0.0]
  LeafBench is a visual question-answering benchmark developed to evaluate the capabilities of Vision-Language Models (VLMs) in understanding plant diseases.<n>The dataset comprises 186,000 leaf digital images spanning 97 disease classes, paired with metadata, generating 13,950 question-answer pairs.<n> Benchmarking 12 state-of-the-art VLMs on our LeafBench dataset, we reveal substantial disparity in their disease understanding capabilities.
  arXiv  Detail & Related papers  (2026-02-14T08:10:27Z)
• Analysis of Plant Nutrient Deficiencies Using Multi-Spectral Imaging and Optimized Segmentation Model [1.4172975813702]
  This study presents a deep learning framework for leaf anomaly segmentation using multispectral imaging and an enhanced YOLOv5 model.<n>The model is tailored for processing nine-channel multispectral input and uses self-attention mechanisms to better capture subtle, spatially-distributed symptoms.
  arXiv  Detail & Related papers  (2025-07-18T15:25:36Z)
• GENERator: A Long-Context Generative Genomic Foundation Model [66.46537421135996]
  We present GENERator, a generative genomic foundation model featuring a context length of 98k base pairs (bp) and 1.2B parameters.<n>Trained on an expansive dataset comprising 386B bp of DNA, the GENERator demonstrates state-of-the-art performance across both established and newly proposed benchmarks.<n>It also shows significant promise in sequence optimization, particularly through the prompt-responsive generation of enhancer sequences with specific activity profiles.
  arXiv  Detail & Related papers  (2025-02-11T05:39:49Z)
• GenBench: A Benchmarking Suite for Systematic Evaluation of Genomic Foundation Models [56.63218531256961]
  We introduce GenBench, a benchmarking suite specifically tailored for evaluating the efficacy of Genomic Foundation Models. GenBench offers a modular and expandable framework that encapsulates a variety of state-of-the-art methodologies. We provide a nuanced analysis of the interplay between model architecture and dataset characteristics on task-specific performance.
  arXiv  Detail & Related papers  (2024-06-01T08:01:05Z)
• BonnBeetClouds3D: A Dataset Towards Point Cloud-based Organ-level Phenotyping of Sugar Beet Plants under Field Conditions [28.79416825695514]
  Agricultural production is facing severe challenges in the next decades induced by climate change and the need for sustainability.<n> Advancements in field management through non-chemical weeding by robots in combination with monitoring of crops by autonomous unmanned aerial vehicles (UAVs) are helpful to address these challenges.<n>The analysis of plant traits, called phenotyping, is an essential activity in plant breeding, it however involves a great amount of manual labor.
  arXiv  Detail & Related papers  (2023-12-22T14:06:44Z)
• Deep Learning for Plant Identification and Disease Classification from Leaf Images: Multi-prediction Approaches [14.73818032506552]
  We survey current deep learning approaches for plant identification and disease classification. We propose a new model named Generalised Stacking Multi-output CNN (GSMo-CNN) We show that the proposed GSMo-CNN achieves state-of-the-art performance on three benchmark datasets.
  arXiv  Detail & Related papers  (2023-10-25T01:06:18Z)
• Semantic Image Segmentation with Deep Learning for Vine Leaf Phenotyping [59.0626764544669]
  In this study, we use Deep Learning methods to semantically segment grapevine leaves images in order to develop an automated object detection system for leaf phenotyping. Our work contributes to plant lifecycle monitoring through which dynamic traits such as growth and development can be captured and quantified.
  arXiv  Detail & Related papers  (2022-10-24T14:37:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.