# From Legacy Fortran to Portable Kokkos: An Autonomous Agentic AI Workflow

arXiv: https://arxiv.org/abs/2509.12443 · HTML: https://mlsanity.com/paper/2509.12443/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 42 references that are in the map.
- First posted on arXiv 15 Sep 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 16 of 16)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules](https://mlsanity.com/paper/2310.08992/) (2023)
- [AI-assisted coding: Experiments with GPT-4](https://mlsanity.com/paper/2304.13187/) (2023)
- [Can Large Language Models Write Parallel Code?](https://mlsanity.com/paper/2401.12554/) (2024)
- [Evaluation of OpenAI Codex for HPC Parallel Programming Models Kernel Generation](https://mlsanity.com/paper/2306.15121/) (2023)
- [Enhancing LLM Code Generation: A Systematic Evaluation of Multi-Agent Collaboration and Runtime Debugging for Improved Accuracy, Reliability, and Latency](https://mlsanity.com/paper/2505.02133/) (2025)
- [LLM-Assisted Translation of Legacy FORTRAN Codes to C++: A Cross-Platform Study](https://mlsanity.com/paper/2504.15424/) (2025)
- [LLM Benchmarking with LLaMA2: Evaluating Code Development Performance Across Multiple Programming Languages](https://mlsanity.com/paper/2503.19217/) (2025)
- [Fortran2CPP: Automating Fortran-to-C++ Translation using LLMs via Multi-Turn Dialogue and Dual-Agent Integration](https://mlsanity.com/paper/2412.19770/) (2024)
- [Many Cores, Many Models: GPU Programming Model vs. Vendor Compatibility Overview](https://mlsanity.com/paper/2309.05445/) (2023)
- [An asynchronous and task-based implementation of Peridynamics utilizing HPX -- the C++ standard library for parallelism and concurrency](https://mlsanity.com/paper/1806.06917/) (2018)

## Built on by (most cited first, 5 of 5)

- [Systematic LLM Translation of Legacy Scientific Code to Differentiable Frameworks: Application to a Land Surface Model](https://mlsanity.com/paper/2606.07681/) (2026)
- [Automated Design Optimization via Strategic Search with Large Language Models](https://mlsanity.com/paper/2511.22651/) (2025)
- [An Agentic Evaluation Framework for AI-Generated Scientific Code in PETSc](https://mlsanity.com/paper/2603.15976/) (2026)
- [An Agentic Workflow for Legacy HPC Modernization: Converting the Two-Electron-Integral Core of GAMESS](https://mlsanity.com/paper/2608.12249/) (2026)
- [From Numerical Simulators of PDEs to Neural Emulators and Back](https://mlsanity.com/paper/2608.24547/) (2026)

## Abstract (arXiv)

Scientific applications continue to rely on legacy Fortran codebases originally developed for homogeneous, CPU-based systems. As High-Performance Computing (HPC) shifts toward heterogeneous GPU-accelerated architectures, many accelerators lack native Fortran bindings, creating an urgent need to modernize legacy codes for portability. Frameworks like Kokkos provide performance portability and a single-source C++ abstraction, but manual Fortran-to-Kokkos porting demands significant expertise and time. Large language models (LLMs) have shown promise in source-to-source code generation, yet their use in fully autonomous workflows for translating and optimizing parallel code remains largely unexplored, especially for performance portability across diverse hardware. This paper presents an agentic AI workflow where specialized LLM "agents" collaborate to translate, validate, compile, run, test, debug, and optimize Fortran kernels into portable Kokkos C++ programs. Results show the pipeline modernizes a range of benchmark kernels, producing performance-portable Kokkos codes across hardware partitions. Paid OpenAI models such as GPT-5 and o4-mini-high executed the workflow for only a few U.S. dollars, generating optimized codes that surpassed Fortran baselines, whereas open-source models like Llama4-Maverick often failed to yield functional codes. This work demonstrates the feasibility of agentic AI for Fortran-to-Kokkos transformation and offers a pathway for autonomously modernizing legacy scientific applications to run portably and efficiently on diverse supercomputers. It further highlights the potential of LLM-driven agentic systems to perform structured, domain-specific reasoning tasks in scientific and systems-oriented applications.