Problem
Research questions and friction points this paper is trying to address.
Agentic AI
Scientific Software Engineering
Code Verification
Collaborative Workflows
Code Translation
Designing Collaborative AI-Driven Workflows for Scientific Software Engineering
🤖 AI Summary
This study addresses the challenges of correctness verification and cross-domain comprehension for AI-generated code in scientific computing by proposing a deterministic, orchestrator-based human-AI collaborative workflow. In this framework, domain experts define specifications while AI agents perform coding, with quality ensured through numerical consistency checks and manual review. The core innovation lies in a lightweight "author-reviewer" loop that replaces complex multi-agent systems to enable efficient Fortran-to-C++ code migration. High-energy physics experiments demonstrate that this streamlined iterative architecture reduces costs to approximately one-third of those incurred by comparable approaches on equivalent tasks, achieving both reliability and cost-effectiveness.
📝 Abstract
Agentic artificial intelligence systems can carry out a broad range of tasks in software engineering and scientific research, from writing and translating code to running workflows for data analysis and visualization. In scientific computing, the difficulty is verifying that agent-generated code is both correct and understandable to teams whose members bring different areas of expertise. We therefore argue that these systems are best used within collaborative team structures rather than as full automation. In the workflows we propose, domain experts write the specification and plan, and agents operate under a deterministic orchestration pattern to write the target code. Each stage ends with a numerical comparison against the reference code and requires human review and approval before the next begins. We evaluate these workflows on the translation of a large high-energy physics application from Fortran to C++, running the same task under different orchestrators, design patterns, and models. Across fourteen experiments, a simple author--reviewer loop with enforced limits completed a comparable number of files to a multi-agent workflow at about one-third of the cost per file.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Agentic AI
Scientific Software Engineering
Collaborative Workflows
Deterministic Orchestration
Code Translation
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
