Design and Implementation of Data Acquisition and Analysis System for Programming Debugging Process Based On VS Code Plug-In

• URL: http://arxiv.org/abs/2511.05825v1
• Date: Sat, 08 Nov 2025 03:18:34 GMT
• Title: Design and Implementation of Data Acquisition and Analysis System for Programming Debugging Process Based On VS Code Plug-In
• Authors: Boyang Liu,
• Abstract summary: This paper implements a data acquisition and analysis system for programming debug process based on VS Code plug-in.<n>The system supports a variety of programming languages, integrates debug tasks and data acquisition functions.<n>It uploads the data to the platform database to realize the whole process monitoring and feedback, and improves the teaching effect.
• Score: 1.1521859713894205
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In order to meet the needs of students' programming debugging ability training, this paper designs and implements a data acquisition and analysis system for programming debugging process based on VS Code plug-in, which aims to solve the limitation of traditional assessment methods that are difficult to fully evaluate students' debugging ability. The system supports a variety of programming languages, integrates debugging tasks and data acquisition functions, captures students' debugging behavior in the local editor in real time, and uploads the data to the platform database to realize the whole process monitoring and feedback, provides accurate debugging guidance for teachers, and improves the teaching effect. In terms of data analysis, the system proposed a debugging behavior analysis model based on abstract syntax tree, combined with node annotation, sequence recognition and cluster analysis and other technologies, to automatically track the context of students' debugging process and accurately identify key features in the debugging path. Through this tool, the system realizes the intelligent identification and labeling of the debugging direction and behavior pattern, and improves the refinement level of debugging data analysis. In this research system, a complex debugging scenario of multi-file and multi-task is introduced into the debugging problem design, which optimizes the multi-dimensional capturing ability of debugging data and lays a foundation for accurate debugging behavior analysis. Through several practical teaching tests, the feasibility and stability of the system are verified, which proves that it can effectively support procedural evaluation in programming debugging teaching, and provides a new direction for debugging behavior analysis research.

Related papers

• Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey [59.3507264893654]
  Issue resolution is a complex Software Engineering task integral to real-world development.<n> benchmarks like SWE-bench revealed this task as profoundly difficult for large language models.<n>This paper presents a systematic survey of this emerging domain.
  arXiv  Detail & Related papers  (2026-01-15T18:55:03Z)
• Enhancing Debugging Skills with AI-Powered Assistance: A Real-Time Tool for Debugging Support [8.607022377771422]
  It offers real-time support by analyzing code, suggesting breakpoints, and providing contextual hints.<n>Using RAG with LLMs, program slicing, and customs, it enhances efficiency by minimizing LLM calls and improving accuracy.
  arXiv  Detail & Related papers  (2026-01-05T19:20:59Z)
• InspectCoder: Dynamic Analysis-Enabled Self Repair through interactive LLM-Debugger Collaboration [71.18377595277018]
  Large Language Models (LLMs) frequently generate buggy code with complex logic errors that are challenging to diagnose.<n>We present InspectCoder, the first agentic program repair system that empowers LLMs to actively conduct dynamic analysis via interactive debugger control.
  arXiv  Detail & Related papers  (2025-10-21T06:26:29Z)
• ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models [81.12673534903979]
  Tool learning has emerged as a crucial capability for large language models (LLMs) to solve complex real-world tasks through interaction with external tools.<n>We propose ToolCoder, a novel framework that reformulates tool learning as a code generation task.
  arXiv  Detail & Related papers  (2025-02-17T03:42:28Z)
• Simulated Interactive Debugging [7.3742419367796535]
  We present our approach called Simulated Interactive that interactively guides students along the debug process.<n>The guidance aims to empower the students to repair their solutions and have a proper learning experience.<n>We developed an implementation using traditional fault localization techniques and large language models.
  arXiv  Detail & Related papers  (2025-01-16T17:47:18Z)
• VDebugger: Harnessing Execution Feedback for Debugging Visual Programs [103.61860743476933]
  We introduce V Debugger, a critic-refiner framework trained to localize and debug visual programs by tracking execution step by step. V Debugger identifies and corrects program errors leveraging detailed execution feedback, improving interpretability and accuracy. Evaluations on six datasets demonstrate V Debugger's effectiveness, showing performance improvements of up to 3.2% in downstream task accuracy.
  arXiv  Detail & Related papers  (2024-06-19T11:09:16Z)
• Efficacy of static analysis tools for software defect detection on open-source projects [0.0]
  The study used popular analysis tools such as SonarQube, PMD, Checkstyle, and FindBugs to perform the comparison. The study results show that SonarQube performs considerably well than all other tools in terms of its defect detection.
  arXiv  Detail & Related papers  (2024-05-20T19:05:32Z)
• LLMDFA: Analyzing Dataflow in Code with Large Language Models [8.92611389987991]
  This paper presents LLMDFA, a compilation-free and customizable dataflow analysis framework. We decompose the problem into several subtasks and introduce a series of novel strategies. On average, LLMDFA achieves 87.10% precision and 80.77% recall, surpassing existing techniques with F1 score improvements of up to 0.35.
  arXiv  Detail & Related papers  (2024-02-16T15:21:35Z)
• Leveraging Print Debugging to Improve Code Generation in Large Language Models [63.63160583432348]
  Large language models (LLMs) have made significant progress in code generation tasks. But their performance in tackling programming problems with complex data structures and algorithms remains suboptimal. We propose an in-context learning approach that guides LLMs to debug by using a "print debug" method.
  arXiv  Detail & Related papers  (2024-01-10T18:37:59Z)
• Teaching Large Language Models to Self-Debug [62.424077000154945]
  Large language models (LLMs) have achieved impressive performance on code generation. We propose Self- Debugging, which teaches a large language model to debug its predicted program via few-shot demonstrations.
  arXiv  Detail & Related papers  (2023-04-11T10:43:43Z)
• Understanding and Supporting Debugging Workflows in Multiverse Analysis [12.23386451120784]
  Multiverse analysis is a paradigm for statistical analysis that considers all combinations of reasonable analysis choices in parallel. Recent tools help analysts specify multiverse analyses, but they remain difficult to use in practice. We develop a command-line interface tool, Multiverse Debugger, which helps diagnose bugs in the multiverse and propagate.
  arXiv  Detail & Related papers  (2022-10-07T20:22:36Z)

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.