AI Agents and Agentic AI in plant breeding: new frontiers, opportunities and challenges

ИИ-агенты и агентный искусственный интеллект в селекции растений: новые рубежи, возможности и вызовы
José Luis Crossa, Osval Antonio Montesinos-López, Susanne Dreisigacker, Guillermo Gerard, Abelardo Montesinos‐López, Deepak Bhaskar Acharya, Paolo Vitale, Rodomiro Ortiz
2026-09-23

AI agentsagentic AIgenetic gainmulti-agent systemsplant breeding
Plant breeding increasingly integrates diverse data sources, including genomic, phenomic, and environmental information, yet current artificial intelligence (AI) applications remain largely isolated analytical tools. Coordinating the entire breeding pipeline, from data collection and quality control to analysis, prediction, and decision-making, remains a challenge. Here we hypothesize that AI Agents and Agentic AI systems, which autonomously execute tasks using reasoning, memory, and tool integration, may orchestrate complex breeding objectives by coordinating specialized agents across multiple data domains. This approach has the potential to enhance breeding efficiency, reduce operational errors, and accelerate genetic gain by connecting previously fragmented processes. Although empirical validations remain forthcoming, the framework presented here provides a conceptual foundation for future implementation and evaluation. While technical, ethical, and institutional challenges exist, implementing such AI frameworks could support breeders in managing the complexity of modern genetic improvement programs, ultimately contributing to enhanced cultivar development and food security.
1
AI Agents and Agentic AI could orchestrate data collection, quality control, analysis, prediction, and decision-making across genomic, phenomic, and environmental domains.
2
Coordinating specialized agents may connect fragmented breeding processes, potentially improving breeding efficiency, reducing operational errors, and accelerating genetic gain.
3
Current AI applications in plant breeding are largely isolated analytical tools and do not yet coordinate the full breeding pipeline.
4
Technical, ethical, and institutional challenges may constrain implementation, despite the potential to support complex genetic improvement programs and cultivar development.
5
The proposed framework is conceptual, and empirical validation of its effectiveness in plant breeding remains forthcoming.

plant breeding pipelines integrating genomic, phenomic, and environmental data

orchestration of complex breeding tasks and decision-making by AI Agents and Agentic AI systems

Publication Details
Publication Date
2026-09-23
Journal
Publisher
ISSN
Cited by
0
Access Type
Author Information
Authors
José Luis Crossa
Osval Antonio Montesinos-López
Susanne Dreisigacker
Guillermo Gerard
Abelardo Montesinos‐López
Deepak Bhaskar Acharya
Paolo Vitale
Rodomiro Ortiz
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%