Aleks: AI powered Multi Agent System for Autonomous Scientific Discovery via Data-Driven Approaches in Plant Science

2025-08-26

AI Summary

Plant science faces bottlenecks including complex experimental design, highly heterogeneous data, and poor reproducibility, hindering research efficiency. To address these challenges, we propose the first memory-augmented multi-agent autonomous scientific discovery system tailored for plant science. It integrates domain-specific knowledge bases, knowledge graphs, natural language processing, and machine learning to enable end-to-end, human-in-the-loop-free exploration—from problem formalization and data preprocessing to interpretable modeling. Our key contributions are: (1) the first application of a memory-enhanced multi-agent collaborative framework to AI-driven plant science discovery; (2) cross-iteration reasoning and iterative strategy optimization to ensure model consistency and interpretability; and (3) identification of biologically significant features in grape red blotch disease prediction, with ablation studies confirming the critical role of domain knowledge integration and the memory module in enhancing both predictive performance and model stability.

Technology Category

• Multiagent Systems: Multiagent Planning
• Machine Learning: Graph-based Machine Learning
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Interdisciplinary science discovery with web data mining
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Modern plant science increasingly relies on large, heterogeneous datasets, but challenges in experimental design, data preprocessing, and reproducibility hinder research throughput. Here we introduce Aleks, an AI-powered multi-agent system that integrates domain knowledge, data analysis, and machine learning within a structured framework to autonomously conduct data-driven scientific discovery. Once provided with a research question and dataset, Aleks iteratively formulated problems, explored alternative modeling strategies, and refined solutions across multiple cycles without human intervention. In a case study on grapevine red blotch disease, Aleks progressively identified biologically meaningful features and converged on interpretable models with robust performance. Ablation studies underscored the importance of domain knowledge and memory for coherent outcomes. This exploratory work highlights the promise of agentic AI as an autonomous collaborator for accelerating scientific discovery in plant sciences.

Problem

• Autonomous AI system for data-driven discovery in plant science
• Addresses challenges in experimental design and data reproducibility
• Integrates domain knowledge with machine learning for scientific exploration

Innovation

• AI multi-agent system for autonomous scientific discovery
• Integrates domain knowledge, data analysis, machine learning
• Iteratively formulates problems and refines solutions autonomously