WeedExpert-R1: Incentivizing Botanical Reasoning in MLLMs with Reinforcement Learning for Precision Weed Grounding

• URL: http://arxiv.org/abs/2607.16492v1
• Date: Fri, 17 Jul 2026 20:33:10 GMT
• Title: WeedExpert-R1: Incentivizing Botanical Reasoning in MLLMs with Reinforcement Learning for Precision Weed Grounding
• Abstract summary: This study introduces WeedExpert-R1, a multimodal model that learns visually grounded botanical reasoning through verifiable rewards.<n>WeedExpert-R1-4B achieved 75.82 percent exact-set precision at an IoU threshold of 0.5, 89.30 percent precision, and 87.81 percent recall.
• Score: 5.155445137665098
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Precision weed control requires species-level identification and instance-level localization. However, conventional object detectors use a closed vocabulary, limiting their deployment across regions, and cannot explain their predictions in complex agricultural scenes. Multimodal large language models (MLLMs) offer visual grounding and reasoning capabilities, but insufficient botanical knowledge can cause hallucinations in fine-grained weed identification. This study introduces WeedExpert-R1, a multimodal model that learns visually grounded botanical reasoning through verifiable rewards. A domain-specific Chain-of-Thought synthesis pipeline combines a human-curated botanical trait dictionary with an Auditor-Synthesizer LLM workflow to generate reasoning data for supervised fine-tuning. Group Relative Policy Optimization is then applied with rewards for format, accuracy, instance count, and response length. Across 37 weed species from six datasets, WeedExpert-R1-4B achieved 75.82 percent exact-set precision at an IoU threshold of 0.5, 89.30 percent precision, and 87.81 percent recall. It outperformed proprietary models, including GPT-5.4 and Gemini-3.1-Pro, and larger open-source models, including Qwen3-VL-30B-Instruct and Gemma-4-31B-it. Results on unseen species further demonstrate its open-vocabulary capability and potential for deployment across diverse regions and crops without retraining.

Related papers

• Synergistic Perception-Reasoning Governance: Grounding Medical MLLMs with Verifiable Anatomical Evidence [45.78409219344429]
  Multimodal large language models (MLLMs) show strong promise for clinical VQA and radiology report generation, yet inference-time hallucinations undermine trustworthy use.<n>We propose a holistic, training-free evidence-injection framework that systematically mitigates hallucinations through dual-side evidence injection.<n>We conduct systematic evaluations on 2 tasks and 5 datasets using textttLLaVA-1.5-7B, texttLLaVA-Med-1.5-7B, texttQwen3-VL-8B/32B, and textttInternVL
  arXiv  Detail & Related papers  (2026-06-30T08:07:25Z)
• Leaf Spectral Reflectance Prediction Using Multi-Head Attention Neural Networks [0.2936007114555107]
  We developed a trait-to-spectra prediction model using a neural network trained on a grapevine-specific dataset.<n>The model was evaluated using stratified 5-fold cross-validation and achieved an average coefficient of determination (R2) of 0.84 and normalized root mean squared error (NRMSE) of 1.52 percent.<n>The proposed model provides a robust framework for generating accurate leaf-level reflectance data, with potential applications in canopy trait retrieval, vineyard monitoring, and remote sensing-driven crop management.
  arXiv  Detail & Related papers  (2026-05-31T19:59:58Z)
• CropVLM: A Domain-Adapted Vision-Language Model for Open-Set Crop Analysis [0.0]
  We present CropVLM, a vision-language model adapted for the agricultural domain via Domain-Specific Semantic Alignment (DSSA)<n>CropVLM is trained on 52,987 manually selected image-caption pairs covering 37 species in natural field conditions.<n>In comprehensive evaluations, CropVLM achieves 72.51% zero-shot classification accuracy, outperforming seven CLIP-style baselines.
  arXiv  Detail & Related papers  (2026-05-05T01:17:27Z)
• Do Generative Metrics Predict YOLO Performance? An Evaluation Across Models, Augmentation Ratios, and Dataset Complexity [43.338311770275745]
  We present a controlled evaluation of synthetic augmentation for YOLOv11 across three single-class detection regimes.<n>We benchmark six GAN-, diffusion-, and hybrid-based generators over augmentation ratios from 10% to 150% of the real training split.<n>For each dataset-generator-augmentation configuration, we compute pre-training dataset metrics under a matched-size bootstrap protocol.
  arXiv  Detail & Related papers  (2026-02-20T03:02:36Z)
• Explainable AI for Diabetic Retinopathy Detection Using Deep Learning with Attention Mechanisms and Fuzzy Logic-Based Interpretability [0.0]
  This paper proposes a hybrid deep learning framework recipe for weed detection.<n>A Generative Adversarial Network (GAN)-based augmentation method was imposed to balance class robustness and better generalize the model.<n> Experimental results yield superior results with 99.33% accuracy, precision, recall, and F1-score on multi-benchmark datasets.
  arXiv  Detail & Related papers  (2025-11-20T12:17:00Z)
• A Hybrid CNN-ViT-GNN Framework with GAN-Based Augmentation for Intelligent Weed Detection in Precision Agriculture [0.0]
  This paper proposes a hybrid deep learning framework recipe for weed detection.<n>A Generative Adversarial Network (GAN)-based augmentation method was imposed to balance class robustness and better generalize the model.<n> Experimental results yield superior results with 99.33% accuracy, precision, recall, and F1-score on multi-benchmark datasets.
  arXiv  Detail & Related papers  (2025-11-19T15:32:08Z)
• When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA [46.50540400870401]
  PsiloQA is a large-scale, multilingual dataset annotated with span-level hallucinations across 14 languages.<n>Our dataset and results advance the development of scalable, fine-grained hallucination detection in multilingual settings.
  arXiv  Detail & Related papers  (2025-10-06T14:36:30Z)
• Escaping the SpuriVerse: Can Large Vision-Language Models Generalize Beyond Seen Spurious Correlations? [37.703287009808896]
  Finetuning can cause spurious correlations to arise between non-essential features and the target labels.<n>We develop a benchmark by sourcing GPT-4o errors on real-world visual-question-answering (VQA) benchmarks.<n>We evaluate 15 open and closed-source LVLMs on SpuriVerse, finding that even state-of-the-art closed-source models struggle significantly.
  arXiv  Detail & Related papers  (2025-06-23T06:11:43Z)
• ZINA: Multimodal Fine-grained Hallucination Detection and Editing [46.2482873419289]
  Multimodal Large Language Models (MLLMs) often generate hallucinations, where the output deviates from the visual content.<n>We propose a novel task of multimodal fine-grained hallucination detection and editing for MLLMs.<n>We present ZINA, a novel method that identifies hallucinated spans at a fine-grained level, classifies their error types into six categories, and suggests appropriate refinements.
  arXiv  Detail & Related papers  (2025-06-16T06:27:59Z)
• WeedsGalore: A Multispectral and Multitemporal UAV-based Dataset for Crop and Weed Segmentation in Agricultural Maize Fields [0.7421845364041001]
  Weeds are one of the major reasons for crop yield loss but current weeding practices fail to manage weeds in an efficient and targeted manner.<n>We present a novel dataset for semantic and instance segmentation of crops and weeds in agricultural maize fields.
  arXiv  Detail & Related papers  (2025-02-18T18:13:19Z)
• GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation [108.2008975785364]
  Graph Inspired Veracity Extrapolation (GIVE) is a novel reasoning method that merges parametric and non-parametric memories to improve accurate reasoning with minimal external input.<n>GIVE guides the LLM agent to select the most pertinent expert data (observe), engage in query-specific divergent thinking (reflect), and then synthesize this information to produce the final output (speak)
  arXiv  Detail & Related papers  (2024-10-11T03:05:06Z)
• Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization [37.55557353462219]
  Pruning is a technique that reduces model size by removing redundant weights, enabling more efficient sparse inference. This paper provides an empirical study across five summarization datasets, two state-of-the-art pruning methods, and five instruction-tuned LLMs. Surprisingly, we find that hallucinations are less prevalent from pruned LLMs than the original models.
  arXiv  Detail & Related papers  (2023-11-15T19:49:24Z)

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.