cs.DCNov 6, 2026

More with Less: Efficient Parallel Scientific Code Translation via an Agent-Skill Workflow

Authors: Jianuo Shen, Pengyi Xu, Bo Zhang

Organizations: Department of Computer Science & Engineering, South China University of Technology, Guangzhou, Guangdong 510006 · Department of Computer Science, Michigan Technological University, Houghton, Michigan 49931

Abstract

Translating parallel scientific codes between HPC programming frameworks is a critical but labor-intensive task. Existing LLM-based approaches rely on fixed sequential pipelines with undifferentiated repair strategies and correctness criteria that do not match scientific computing practice. We present an agent-skill framework that separates translation, compilation diagnosis, and execution validation into three autonomous agents coordinated by a verdict-driven orchestrator, routing each failure to a targeted repair skill rather than retrying blindly. An automated output check drives the self-correction loop, complemented by an offline LLM-based verification that exposes false positives escaping compiler and runtime checks. We evaluate the framework on 30 HeCBench kernels translated bidirectionally among CUDA, OpenMP, and SYCL with three open-source LLMs. Our framework attains the higher verified correctness rate in all 18 model and direction combinations over a state-of-the-art baseline while consuming up to 52.4% fewer tokens, remaining consistent across models and directions without architectural modification.

Figures & tables

Explore similar work

CardsList
  1. Can Agentic LLMs Write Task-Based Parallel Code? A Study of OpenMP Tasking, HPX, StarPU and TTG

    Nov 14, 2026Linus Bantel, Anna-Lena Roth, Tim Thüring +2Code GenerationLLM-Based Program Synthesis

  2. Re4: Scientific Computing Agent with Rewriting, Resolution, Review and Revision

    Aug 28, 2025Ao Cheng, Lei Zhang, Guowei HeScientific ComputingScientific Code Generation

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

    Sep 15, 2025Sparsh Gupta, Kamalavasan Kamalakkannan, Maxim Moraru +2Code TranslationAgentic Code Generation