App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 5

Method for god class detection by fusing structural feature attribution and multi-agent reasoning with large language models

Shao Ningning
Liu Chen
Business School, University of Shanghai for Science and Technology, Shanghai 200093, China
DOI: 10.19734/j.issn.1001-3695.2025.10.0389

Abstract

God Class is a typical code smell that reduces software extensibility and maintainability and increases failure risk and maintenance cost. This paper proposes a cooperative multi-agent method that fused structural feature attribution with large-language-model reasoning to detect God Classes. Gradient-boosted trees with SHAP attribution perform feature selection and evidence construction, and builds a complexity-aware prompt accordingly. Multiple agents then engage in round-based debate under light constraints, share a unified global context and evidence view, and adaptively triggers and stops them. The method finally forms the decision by a convex combination of the agents’ detection probability and the structural prior with learnable weights. Experiments show that the method outperforms existing baselines while maintaining decision consistency with Cohen’s κ ≥ 0.75. On cross-project MLCQ datasets, the F1-score improved by 14.6%~76.1% and the false-positive rate decreased by 37.6%~80.4%. The approach provides high recall with low false positives.

Foundation Support

国家社科基金资助项目(24BGL281)
国家自然科学基金资助项目(72574145)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.10.0389
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 5

Publish History

[2026-01-19] Accepted Paper

Cite This Article

邵宁宁, 刘臣. 融合结构特征归因与多智能体推理的上帝类检测方法 [J]. 计算机应用研究, 2026, 43 (5). (2026-01-20). https://doi.org/10.19734/j.issn.1001-3695.2025.10.0389. (Shao Ningning, Liu Chen. Method for god class detection by fusing structural feature attribution and multi-agent reasoning with large language models [J]. Application Research of Computers, 2026, 43 (5). (2026-01-20). https://doi.org/10.19734/j.issn.1001-3695.2025.10.0389. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)