Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.18764 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910234226720768 |
|---|---|
| author | Ali, Hyacinth Galasso-Carbonnel, Jessie Sahraoui, Houari |
| author_facet | Ali, Hyacinth Galasso-Carbonnel, Jessie Sahraoui, Houari |
| contents | Artificial Intelligence (AI) pipelines have become integral to modern research, supporting fields such as Medical Sciences, Agriculture, and Social Sciences, and enabling large-scale data analysis, predictive modeling, and the automation of complex tasks. However, designing and implementing AI solutions remains challenging for many researchers due to the expertise required in the design and development of end-to-end AI systems. To address this gap, we present Domain-Driven Adaptable AI Pipelines (DDAP), a controlled, human-in-the-loop, agentic framework that leverages large language models to guide users in a systematic construction of AI pipelines and their corresponding implementation code. DDAP structures the development process into four stages: problem definition, compute environment specification, pipeline generation, and code generation. Through this staged interaction, the framework adapts to domain context, user expertise, and resource constraints, while maintaining user control over key decisions. We evaluate DDAP across multiple datasets spanning business, biology, and health science domains by comparing its AI models against expert-developed models. The experimental results show that DDAP achieves competitive results in several tasks compared to expert baselines, although performance varies across problem types, particularly for text-based clustering tasks. By combining guided interaction, adaptability, and reproducibility, DDAP demonstrates that a controlled agentic framework can generate competitive AI pipelines for non-expert users. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_18764 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Intent to AI Pipelines: A Controlled Agentic Framework for Non-AI Expert Scientists Ali, Hyacinth Galasso-Carbonnel, Jessie Sahraoui, Houari Information Retrieval Artificial Intelligence Artificial Intelligence (AI) pipelines have become integral to modern research, supporting fields such as Medical Sciences, Agriculture, and Social Sciences, and enabling large-scale data analysis, predictive modeling, and the automation of complex tasks. However, designing and implementing AI solutions remains challenging for many researchers due to the expertise required in the design and development of end-to-end AI systems. To address this gap, we present Domain-Driven Adaptable AI Pipelines (DDAP), a controlled, human-in-the-loop, agentic framework that leverages large language models to guide users in a systematic construction of AI pipelines and their corresponding implementation code. DDAP structures the development process into four stages: problem definition, compute environment specification, pipeline generation, and code generation. Through this staged interaction, the framework adapts to domain context, user expertise, and resource constraints, while maintaining user control over key decisions. We evaluate DDAP across multiple datasets spanning business, biology, and health science domains by comparing its AI models against expert-developed models. The experimental results show that DDAP achieves competitive results in several tasks compared to expert baselines, although performance varies across problem types, particularly for text-based clustering tasks. By combining guided interaction, adaptability, and reproducibility, DDAP demonstrates that a controlled agentic framework can generate competitive AI pipelines for non-expert users. |
| title | From Intent to AI Pipelines: A Controlled Agentic Framework for Non-AI Expert Scientists |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2605.18764 |