AI Agent for Reverse-Engineering Legacy Finite-Difference Code and Translating to Devito

TL;DR

This paper presents an AI agent framework that automates the reverse engineering and translation of legacy finite difference code into the Devito environment using advanced retrieval, static analysis, and reinforcement learning techniques.

Contribution

It introduces a novel hybrid architecture combining RAG, knowledge graphs, and reinforcement learning for dynamic, adaptive code translation and analysis.

Findings

Effective knowledge graph construction from source code

Enhanced retrieval performance via GraphRAG optimization

Improved code translation accuracy with feedback mechanisms

Abstract

To facilitate the transformation of legacy finite difference implementations into the Devito environment, this study develops an integrated AI agent framework. Retrieval-Augmented Generation (RAG) and open-source Large Language Models are combined through multi-stage iterative workflows in the system's hybrid LangGraph architecture. The agent constructs an extensive Devito knowledge graph through document parsing, structure-aware segmentation, extraction of entity relationships, and Leiden-based community detection. GraphRAG optimisation enhances query performance across semantic communities that include seismic wave simulation, computational fluid dynamics, and performance tuning libraries. A reverse engineering component derives three-level query strategies for RAG retrieval through static analysis of Fortran source code. To deliver precise contextual information for language model guidance, the multi-stage retrieval pipeline performs parallel searching, concept expansion, community-scale retrieval, and semantic similarity analysis. Code synthesis is governed by Pydantic-based constraints to guarantee structured outputs and reliability. A comprehensive validation framework integrates conventional static analysis with the G-Eval approach, covering execution correctness, structural soundness, mathematical consistency, and API compliance. The overall agent workflow is implemented on the LangGraph framework and adopts concurrent processing to support quality-based iterative refinement and state-aware dynamic routing. The principal contribution lies in the incorporation of feedback mechanisms motivated by reinforcement learning, enabling a transition from static code translation toward dynamic and adaptive analytical behavior.