Ten Simple Rules for AI-Assisted Coding in Science

2025-10-25

AI Summary

AI-powered coding tools face significant challenges in scientific computing, including insufficient code reliability, reproducibility, and scientific validity. Method: This paper introduces the first systematic framework of AI-augmented programming guidelines tailored for scientific research, comprising ten actionable principles spanning problem modeling, human–AI collaborative interaction, domain-knowledge integration, automated testing, numerical verification, and iterative optimization. The framework integrates AI code generation with scientific software engineering best practices—incorporating numerical validation, unit testing, and result traceability—while explicitly preserving human researchers’ decision-making authority and the irreplaceable role of domain expertise. Contribution/Results: Evaluated across multiple scientific computing domains, the framework significantly improves development efficiency while rigorously ensuring scientific rigor, computational reproducibility, and methodological reliability.

Technology Category

• Humans and AI: Other Foundations of Human Computation & AI
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

While AI coding tools have demonstrated potential to accelerate software development, their use in scientific computing raises critical questions about code quality and scientific validity. In this paper, we provide ten practical rules for AI-assisted coding that balance leveraging capabilities of AI with maintaining scientific and methodological rigor. We address how AI can be leveraged strategically throughout the development cycle with four key themes: problem preparation and understanding, managing context and interaction, testing and validation, and code quality assurance and iterative improvement. These principles serve to emphasize maintaining human agency in coding decisions, establishing robust validation procedures, and preserving the domain expertise essential for methodologically sound research. These rules are intended to help researchers harness AI's transformative potential for faster software development while ensuring that their code meets the standards of reliability, reproducibility, and scientific validity that research integrity demands.

Problem

• Addressing code quality and scientific validity in AI-assisted scientific computing
• Balancing AI capabilities with scientific rigor throughout development cycles
• Ensuring reliability and reproducibility while accelerating software development

Innovation

• Establishing human agency in coding decisions
• Implementing robust validation procedures for code
• Preserving domain expertise for scientific validity