Spec-Driven AI for Science: The ARIA Framework for Automated and Reproducible Data Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914089769369600 |
|---|---|
| author | Chen, Chuke Luo, Biao Li, Nan Wang, Boxiang Yang, Hang Guo, Jing Xu, Ming |
| author_facet | Chen, Chuke Luo, Biao Li, Nan Wang, Boxiang Yang, Hang Guo, Jing Xu, Ming |
| contents | The rapid expansion of scientific data has widened the gap between analytical capability and research intent. Existing AI-based analysis tools, ranging from AutoML frameworks to agentic research assistants, either favor automation over transparency or depend on manual scripting that hinders scalability and reproducibility. We present ARIA (Automated Research Intelligence Assistant), a spec-driven, human-in-the-loop framework for automated and interpretable data analysis. ARIA integrates six interoperable layers, namely Command, Context, Code, Data, Orchestration, and AI Module, within a document-centric workflow that unifies human reasoning and machine execution. Through natural-language specifications, researchers define analytical goals while ARIA autonomously generates executable code, validates computations, and produces transparent documentation. Beyond achieving high predictive accuracy, ARIA can rapidly identify optimal feature sets and select suitable models, minimizing redundant tuning and repetitive experimentation. In the Boston Housing case, ARIA discovered 25 key features and determined XGBoost as the best performing model (R square = 0.93) with minimal overfitting. Evaluations across heterogeneous domains demonstrate ARIA's strong performance, interpretability, and efficiency compared with state-of-the-art systems. By combining AI for research and AI for science principles within a spec-driven architecture, ARIA establishes a new paradigm for transparent, collaborative, and reproducible scientific discovery. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_11143 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Spec-Driven AI for Science: The ARIA Framework for Automated and Reproducible Data Analysis Chen, Chuke Luo, Biao Li, Nan Wang, Boxiang Yang, Hang Guo, Jing Xu, Ming Artificial Intelligence Human-Computer Interaction 68U35, 62P30 I.2.2 The rapid expansion of scientific data has widened the gap between analytical capability and research intent. Existing AI-based analysis tools, ranging from AutoML frameworks to agentic research assistants, either favor automation over transparency or depend on manual scripting that hinders scalability and reproducibility. We present ARIA (Automated Research Intelligence Assistant), a spec-driven, human-in-the-loop framework for automated and interpretable data analysis. ARIA integrates six interoperable layers, namely Command, Context, Code, Data, Orchestration, and AI Module, within a document-centric workflow that unifies human reasoning and machine execution. Through natural-language specifications, researchers define analytical goals while ARIA autonomously generates executable code, validates computations, and produces transparent documentation. Beyond achieving high predictive accuracy, ARIA can rapidly identify optimal feature sets and select suitable models, minimizing redundant tuning and repetitive experimentation. In the Boston Housing case, ARIA discovered 25 key features and determined XGBoost as the best performing model (R square = 0.93) with minimal overfitting. Evaluations across heterogeneous domains demonstrate ARIA's strong performance, interpretability, and efficiency compared with state-of-the-art systems. By combining AI for research and AI for science principles within a spec-driven architecture, ARIA establishes a new paradigm for transparent, collaborative, and reproducible scientific discovery. |
| title | Spec-Driven AI for Science: The ARIA Framework for Automated and Reproducible Data Analysis |
| topic | Artificial Intelligence Human-Computer Interaction 68U35, 62P30 I.2.2 |
| url | https://arxiv.org/abs/2510.11143 |