Code Digital Twin: Empowering LLMs with Tacit Knowledge for Complex Software Maintenance

• URL: http://arxiv.org/abs/2503.07967v1
• Date: Tue, 11 Mar 2025 01:46:58 GMT
• Title: Code Digital Twin: Empowering LLMs with Tacit Knowledge for Complex Software Maintenance
• Authors: Xin Peng, Chong Wang, Mingwei Liu, Yiling Lou, Yijian Wu,
• Abstract summary: We introduce the concept and framework of textbfCode Digital Twin, a conceptual representation of tacit knowledge.<n>A code digital twin is constructed using a methodology that combines knowledge extraction from both structured and unstructured sources.
• Score: 9.603528792596348
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While large language models (LLMs) have demonstrated promise in software engineering tasks like code completion and generation, their support for the maintenance of complex software systems remains limited. These models often struggle with understanding the tacit knowledge embedded in systems, such as responsibility allocation and collaboration across different modules. To address this gap, we introduce the concept and framework of \textbf{Code Digital Twin}, a conceptual representation of tacit knowledge that captures the concepts, functionalities, and design rationales behind code elements, co-evolving with the software. A code digital twin is constructed using a methodology that combines knowledge extraction from both structured and unstructured sources--such as source code, documentation, and change histories--leveraging LLMs, static analysis tools, and human expertise. This framework can empower LLMs for software maintenance tasks such as issue localization and repository-level code generation by providing tacit knowledge as contexts. Based on the proposed methodology, we explore the key challenges and opportunities involved in the continuous construction and refinement of code digital twin.

Related papers

• An Empirical Study on the Effectiveness of Large Language Models for Binary Code Understanding [50.17907898478795]
  This work proposes a benchmark to evaluate the effectiveness of Large Language Models (LLMs) in real-world reverse engineering scenarios. Our evaluations reveal that existing LLMs can understand binary code to a certain extent, thereby improving the efficiency of binary code analysis.
  arXiv  Detail & Related papers  (2025-04-30T17:02:06Z)
• Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs [53.00384299879513]
  In large language models (LLMs), code and reasoning reinforce each other.<n>Code provides verifiable execution paths, enforces logical decomposition, and enables runtime validation.<n>We identify key challenges and propose future research directions to strengthen this synergy.
  arXiv  Detail & Related papers  (2025-02-26T18:55:42Z)
• Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation [58.799397354312596]
  Large language models (LLMs) have demonstrated remarkable capabilities in various domains, particularly in system 1 tasks.<n>Recent research on System2-to-System1 methods surge, exploring the System 2 reasoning knowledge via inference-time computation.<n>In this paper, we focus on code generation, which is a representative System 2 task, and identify two primary challenges.
  arXiv  Detail & Related papers  (2025-02-18T03:20:50Z)
• Specifications: The missing link to making the development of LLM systems an engineering discipline [65.10077876035417]
  We discuss the progress the field has made so far-through advances like structured outputs, process supervision, and test-time compute.<n>We outline several future directions for research to enable the development of modular and reliable LLM-based systems.
  arXiv  Detail & Related papers  (2024-11-25T07:48:31Z)
• Codellm-Devkit: A Framework for Contextualizing Code LLMs with Program Analysis Insights [9.414198519543564]
  We present codellm-devkit (hereafter, CLDK'), an open-source library that significantly simplifies the process of performing program analysis. CLDK offers developers an intuitive and user-friendly interface, making it incredibly easy to provide rich program analysis context to code LLMs.
  arXiv  Detail & Related papers  (2024-10-16T20:05:59Z)
• CodeMMLU: A Multi-Task Benchmark for Assessing Code Understanding Capabilities of CodeLLMs [9.649864680130781]
  We present CodeMMLU, a benchmark designed to evaluate the depth of software and code understanding in CodeLLMs.<n>CodeMMLU includes over 10,000 questions sourced from diverse domains, encompassing tasks such as code analysis, defect detection, and software engineering principles.<n>Our evaluation reveals that even state-of-the-art models face significant challenges with CodeMMLU.
  arXiv  Detail & Related papers  (2024-10-02T20:04:02Z)
• Code-Survey: An LLM-Driven Methodology for Analyzing Large-Scale Codebases [3.8153349016958074]
  We introduce Code-Survey, the first LLM-driven methodology designed to explore and analyze large-scales. By carefully designing surveys, Code-Survey transforms unstructured data, such as commits, emails, into organized, structured, and analyzable datasets. This enables quantitative analysis of complex software evolution and uncovers valuable insights related to design, implementation, maintenance, reliability, and security.
  arXiv  Detail & Related papers  (2024-09-24T17:08:29Z)
• How Far Have We Gone in Binary Code Understanding Using Large Language Models [51.527805834378974]
  We propose a benchmark to evaluate the effectiveness of Large Language Models (LLMs) in binary code understanding. Our evaluations reveal that existing LLMs can understand binary code to a certain extent, thereby improving the efficiency of binary code analysis.
  arXiv  Detail & Related papers  (2024-04-15T14:44:08Z)
• CodeTF: One-stop Transformer Library for State-of-the-art Code LLM [72.1638273937025]
  We present CodeTF, an open-source Transformer-based library for state-of-the-art Code LLMs and code intelligence. Our library supports a collection of pretrained Code LLM models and popular code benchmarks. We hope CodeTF is able to bridge the gap between machine learning/generative AI and software engineering.
  arXiv  Detail & Related papers  (2023-05-31T05:24:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.