# Spec-Driven AI for Science: The ARIA Framework for Automated and Reproducible Data Analysis

arXiv: https://arxiv.org/abs/2510.11143 · HTML: https://mlsanity.com/paper/2510.11143/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 8 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Builds on (most cited first, 3 of 3)

- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [AgentRxiv: Towards Collaborative Autonomous Research](https://mlsanity.com/paper/2503.18102/) (2025)
- [SPIO: Ensemble and Selective Strategies via LLM-Based Multi-Agent Planning in Automated Data Science](https://mlsanity.com/paper/2503.23314/) (2025)

## Built on by (most cited first, 1 of 1)

- [I-CARE: Analysis of interference-related phenomena in a controllable, diverse and representative unlearning setting for text-to-image models](https://mlsanity.com/paper/2609.00003/) (2026)

## Abstract (arXiv)

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.