PhenoAssistant: A Conversational Multi-Agent AI System for Automated Plant Phenotyping

Abstract

Plant phenotyping increasingly relies on (semi-)automated image-based analysis workflows to improve its accuracy and scalability. However, many existing solutions remain overly complex, difficult to reimplement and maintain, and pose high barriers for users without substantial computational expertise. To address these challenges, we introduce PhenoAssistant: a pioneering AI-driven system that streamlines plant phenotyping via intuitive natural language interaction. PhenoAssistant leverages a large language model to orchestrate a curated toolkit supporting tasks including automated phenotype extraction, data visualisation and automated model training. We validate PhenoAssistant through several representative case studies and a set of evaluation tasks. By significantly lowering technical hurdles, PhenoAssistant underscores the promise of AI-driven methodologies to democratising AI adoption in plant biology.

Plant phenotyping relevance

植物フェノタイピングの画像解析ワークフローを自然言語で自動化するシステムを開発し、ケーススタディと評価タスクで検証しているため、方法が中心である。

Code and data availability

The paper's authors release PhenoAssistant's code, chat logs, and evaluation results on GitHub, and the winter wheat nutrient-deficiency dataset used in Case Study 3 is publicly available on CodaLab. Case Study 1 demonstration data is request-only (Phenotiki), and Case Study 2 data is on Zenodo, which is not among the审