Species delimitation 4.0: Integrative taxonomy meets artificial intelligence Species are fundamental units in biological research, but recent genomic findings highlight that species definitions based solely on morphology may be flawed, especially in groups with complex evolutionary processes like hybridization, polyploidy, and asexuality. Current integrative taxonomy, combining genetics, morphology, and ecology, faces challenges such as differing species concepts, lack of universal markers, and subjective data integration. Integrative taxonomy combined with artificial intelligence (AI) can reduce subjectivity by enabling automated feature learning and data integration, accelerating the revision of eukaryotic biodiversity. The global eukaryotic species count is estimated at over 2 million, with significant gaps in describing species, particularly in animals and protists. Species delimitation has been a long-standing debate, with various species concepts leading to inconsistent results. The unified species concept (USC) provides a framework for species delimitation, applicable to asexual and hybrid species. However, traditional methods face challenges in accurately defining species due to complex evolutionary processes. Species delimitation has evolved through four stages: 1.0 (morphology), 2.0 (genetics), 3.0 (integrative taxonomy), and 4.0 (AI integration). AI can help reduce subjectivity and improve accuracy by integrating genetic, morphological, ecological, and other data. Machine learning (ML) techniques, including supervised and unsupervised learning, are being used to analyze large datasets and identify species. Deep learning (DL) is particularly effective for feature extraction and learning from data. Hybridization, polyploidy, and asexuality complicate species delimitation, as these processes can lead to reticulate evolution and hybrid offspring. AI can help detect gene flow, lineage stability, and hybrid origins. Polyploidy increases genetic flexibility and can lead to new species in a short time. Asexuality is linked to hybridization and polyploidy, and can result in self-fertilization and asexual reproduction. Species concepts vary, but the USC is widely accepted for defining species. Integrative taxonomy combines multiple data sources to improve species delimitation. AI-based approaches, such as machine learning, can enhance the accuracy and efficiency of species delimitation by integrating genetic, morphological, and ecological data. However, challenges remain in handling dataset biases, ensuring model accuracy, and validating results. Future research should focus on improving AI models for species delimitation, integrating multi-approach data, and developing standardized methods. AI can help address the challenges of species delimitation in a world of declining biodiversity, providing more reliable and objective results. The integration of AI with integrative taxonomy represents a promising approach for advancing species delimitation and biodiversity research.Species delimitation 4.0: Integrative taxonomy meets artificial intelligence Species are fundamental units in biological research, but recent genomic findings highlight that species definitions based solely on morphology may be flawed, especially in groups with complex evolutionary processes like hybridization, polyploidy, and asexuality. Current integrative taxonomy, combining genetics, morphology, and ecology, faces challenges such as differing species concepts, lack of universal markers, and subjective data integration. Integrative taxonomy combined with artificial intelligence (AI) can reduce subjectivity by enabling automated feature learning and data integration, accelerating the revision of eukaryotic biodiversity. The global eukaryotic species count is estimated at over 2 million, with significant gaps in describing species, particularly in animals and protists. Species delimitation has been a long-standing debate, with various species concepts leading to inconsistent results. The unified species concept (USC) provides a framework for species delimitation, applicable to asexual and hybrid species. However, traditional methods face challenges in accurately defining species due to complex evolutionary processes. Species delimitation has evolved through four stages: 1.0 (morphology), 2.0 (genetics), 3.0 (integrative taxonomy), and 4.0 (AI integration). AI can help reduce subjectivity and improve accuracy by integrating genetic, morphological, ecological, and other data. Machine learning (ML) techniques, including supervised and unsupervised learning, are being used to analyze large datasets and identify species. Deep learning (DL) is particularly effective for feature extraction and learning from data. Hybridization, polyploidy, and asexuality complicate species delimitation, as these processes can lead to reticulate evolution and hybrid offspring. AI can help detect gene flow, lineage stability, and hybrid origins. Polyploidy increases genetic flexibility and can lead to new species in a short time. Asexuality is linked to hybridization and polyploidy, and can result in self-fertilization and asexual reproduction. Species concepts vary, but the USC is widely accepted for defining species. Integrative taxonomy combines multiple data sources to improve species delimitation. AI-based approaches, such as machine learning, can enhance the accuracy and efficiency of species delimitation by integrating genetic, morphological, and ecological data. However, challenges remain in handling dataset biases, ensuring model accuracy, and validating results. Future research should focus on improving AI models for species delimitation, integrating multi-approach data, and developing standardized methods. AI can help address the challenges of species delimitation in a world of declining biodiversity, providing more reliable and objective results. The integration of AI with integrative taxonomy represents a promising approach for advancing species delimitation and biodiversity research.