{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T06:07:40Z","timestamp":1783577260153,"version":"3.55.0"},"reference-count":82,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T00:00:00Z","timestamp":1772582400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Code smells\u2014subtle indicators of poor design choices\u2014pose significant challenges to software maintainability and readability, particularly in dynamic languages such as Python. Traditional detection methods, including rule-based heuristics and static machine learning classifiers, often suffer from limited adaptability, poor contextual awareness, and lack of explainability. These limitations hinder their effectiveness in evolving codebases and real-world development environments. This study introduces a novel Agentic retrieval-augmented generation (Agentic RAG) framework for code smell detection, marking the first application of agentic reasoning in this domain. By embedding autonomous agents into the retrieval and reasoning pipeline, the proposed system dynamically routes queries, selects optimal retrieval strategies, and synthesizes context-aware explanations using large language models (LLMs). Unlike static classifiers, the proposed framework leverages hybrid retrieval (sparse + dense) and structured prompting to detect and explain Long Method and Large Class smells with high interpretability. Experimental results demonstrate that Agentic RAG\u2014particularly when paired with DeepSeek and chain-of-thought prompting\u2014achieves superior performance, with 89.5% accuracy, a macro F1-score of 78.3%, and a weighted F1 of 88.7%. To assess generalization, Experiment 2 extended the framework to 21 distinct code smell types across multiple programming languages, achieving 94.85% accuracy, a macro F1-score of 90.24%, and a weighted F1-score of 94.93% through stratified five-fold cross-validation, thereby confirming the model\u2019s robustness and scalability. Beyond academic benchmarks, this work lays the foundation for real-world integration into developer platforms, enabling real-time code review, contextual feedback, and actionable refactoring suggestions. By bridging LLMs with dynamic retrieval and agentic reasoning, this framework advances the frontier of intelligent software quality assurance.<\/jats:p>","DOI":"10.7717\/peerj-cs.3642","type":"journal-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T08:23:22Z","timestamp":1772612602000},"page":"e3642","source":"Crossref","is-referenced-by-count":1,"title":["Pioneering agentic retrieval-augmented generation in software quality: a novel framework for code smell detection\n                    <i>via<\/i>\n                    dynamic retrieval"],"prefix":"10.7717","volume":"12","author":[{"given":"Bushra","family":"Aljohani","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdulmajeed","family":"Aljuhani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2026,3,4]]},"reference":[{"key":"10.7717\/peerj-cs.3642\/ref-1","doi-asserted-by":"publisher","first-page":"116462\u2013116472","DOI":"10.1109\/ACCESS.2025.3586203","article-title":"Leveraging RAG and LLMs for access control policy extraction from user stories in agile software development","volume":"13","author":"Aboukadri","year":"2025","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3642\/ref-2","first-page":"82","article-title":"Augmenting large language models with static code analysis for automated code quality improvements","author":"Abtahi","year":"2025"},{"issue":"4","key":"10.7717\/peerj-cs.3642\/ref-3","doi-asserted-by":"publisher","first-page":"2341","DOI":"10.1007\/s13369-019-04311-w","article-title":"Bad smell detection using machine learning techniques: a systematic literature review","volume":"45","author":"Al-Shaaby","year":"2020","journal-title":"Arabian Journal for Science and Engineering"},{"key":"10.7717\/peerj-cs.3642\/ref-4","first-page":"295","article-title":"Establishing traceability between natural language requirements and software artifacts by combining RAG and LLMs","author":"Ali","year":"2024"},{"key":"10.7717\/peerj-cs.3642\/ref-5","doi-asserted-by":"publisher","first-page":"e2254","DOI":"10.7717\/peerj-cs.2254","article-title":"Dynamic stacking ensemble for cross-language code smell detection","volume":"10","author":"Aljamaan","year":"2024","journal-title":"PeerJ Computer Science"},{"issue":"2","key":"10.7717\/peerj-cs.3642\/ref-6","doi-asserted-by":"publisher","first-page":"106736","DOI":"10.1016\/j.infsof.2021.106736","article-title":"A comparison of machine learning algorithms on design smell detection using balanced and imbalanced dataset: a study of god class","volume":"143","author":"Alkharabsheh","year":"2022","journal-title":"Information and Software Technology"},{"issue":"1","key":"10.7717\/peerj-cs.3642\/ref-7","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1038\/s41597-025-05465-z","article-title":"Smellycode++: multi-label dataset for code smell detection","volume":"12","author":"Alomari","year":"2025","journal-title":"Scientific Data"},{"key":"10.7717\/peerj-cs.3642\/ref-8","doi-asserted-by":"crossref","DOI":"10.1109\/COMPSAC65507.2025.00221","article-title":"Bad smell detection using google gemini","author":"Amorim","year":"2025"},{"key":"10.7717\/peerj-cs.3642\/ref-9","first-page":"1","article-title":"Teaching UML using a RAG-based LLM","author":"Ardimento","year":"2024"},{"issue":"1","key":"10.7717\/peerj-cs.3642\/ref-10","first-page":"245","article-title":"Improving legacy software quality through AI-driven code smell detection","volume":"1","author":"Balasubramanian","year":"2021","journal-title":"ESP Journal of Engineering & Technology Advancements"},{"key":"10.7717\/peerj-cs.3642\/ref-11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/EIT63098.2024.10762501","article-title":"Multi-label code smell detection method based on codebert","author":"Bao","year":"2024"},{"key":"10.7717\/peerj-cs.3642\/ref-12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2504.20434","article-title":"ARCS: agentic retrieval-augmented code synthesis with iterative refinement ccs concepts acm reference format","author":"Bhattarai","year":"2025"},{"key":"10.7717\/peerj-cs.3642\/ref-13","volume-title":"Evaluating large language models for code smell detection","author":"Blaauwendraad","year":"2025"},{"issue":"2","key":"10.7717\/peerj-cs.3642\/ref-14","doi-asserted-by":"publisher","first-page":"114076","DOI":"10.1016\/j.eswa.2020.114076","article-title":"Code smell detection and identification in imbalanced environments","volume":"166","author":"Boutaib","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"10.7717\/peerj-cs.3642\/ref-15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2504.02111","article-title":"Exploring llm reasoning through controlled prompt variations","author":"Chatziveroglou","year":"2025","journal-title":"ArXiv preprint"},{"key":"10.7717\/peerj-cs.3642\/ref-16","first-page":"1022","article-title":"Autoreview: an LLM-based multi-agent system for security issue-oriented code review","author":"Chen","year":"2025"},{"issue":"1","key":"10.7717\/peerj-cs.3642\/ref-17","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s12864-019-6413-7","article-title":"The advantages of the matthews correlation coefficient (MCC) over F1-score and accuracy in binary classification evaluation","volume":"21","author":"Chicco","year":"2020","journal-title":"BMC Genomics"},{"key":"10.7717\/peerj-cs.3642\/ref-18","first-page":"32","article-title":"LLM-driven code refactoring: opportunities and limitations","author":"Cordeiro","year":"2025"},{"key":"10.7717\/peerj-cs.3642\/ref-19","doi-asserted-by":"publisher","first-page":"162869\u2013162883","DOI":"10.1109\/access.2021.3133810","article-title":"A novel approach for code smell detection: an empirical study","volume":"9","author":"Dewangan","year":"2021","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3642\/ref-20","first-page":"612","article-title":"Detecting code smells using machine learning techniques: are we there yet?","author":"Di Nucci","year":"2018"},{"key":"10.7717\/peerj-cs.3642\/ref-21","first-page":"1","article-title":"Tuning deepseek-coder-v2-lite-base for C# code smell detection: advancing towards task versatility in software maintenance","author":"Elezi","year":"2025"},{"key":"10.7717\/peerj-cs.3642\/ref-22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2002.08155","article-title":"CodeBERT: a pre-trained model for programming and natural languages","author":"Feng","year":"2020"},{"issue":"2","key":"10.7717\/peerj-cs.3642\/ref-23","doi-asserted-by":"publisher","first-page":"5\u20131","DOI":"10.5381\/jot.2012.11.2.a5","article-title":"Automatic detection of bad smells in code: an experimental assessment","volume":"11","author":"Fontana","year":"2012","journal-title":"The Journal of Object Technology"},{"key":"10.7717\/peerj-cs.3642\/ref-24","first-page":"396","article-title":"Code smell detection: towards a machine learning-based approach","author":"Fontana","year":"2013"},{"key":"10.7717\/peerj-cs.3642\/ref-25","volume-title":"Refactoring: improving the design of existing code","author":"Fowler","year":"2018"},{"key":"10.7717\/peerj-cs.3642\/ref-26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2008.05756","article-title":"Metrics for multi-class classification: an overview","author":"Grandini","year":"2020"},{"issue":"4","key":"10.7717\/peerj-cs.3642\/ref-27","doi-asserted-by":"publisher","first-page":"307","DOI":"10.24138\/jcomss-2024-0083","article-title":"Unsupervised machine learning for effective code smell detection: a novel method","volume":"20","author":"Gupta","year":"2024","journal-title":"Journal of Communications Software and Systems"},{"issue":"5","key":"10.7717\/peerj-cs.3642\/ref-28","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1007\/s42979-024-02956-5","article-title":"Application of deep learning for code smell detection: challenges and opportunities","volume":"5","author":"Hadj-Kacem","year":"2024","journal-title":"SN Computer Science"},{"key":"10.7717\/peerj-cs.3642\/ref-29","doi-asserted-by":"publisher","first-page":"12966","DOI":"10.1109\/ACCESS.2025.3530927","article-title":"Smell-ML: a machine learning framework for detecting rarely studied code smells","volume":"13","author":"Hamouda","year":"2025","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3642\/ref-30","first-page":"54","article-title":"Identification of code smell using machine learning","author":"Jesudoss","year":"2019"},{"key":"10.7717\/peerj-cs.3642\/ref-31","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1145\/1390681.1390698","article-title":"Estimating the confidence interval for prediction errors of support vector machine classifiers","volume":"9","author":"Jiang","year":"2008","journal-title":"The Journal of Machine Learning Research"},{"issue":"4","key":"10.7717\/peerj-cs.3642\/ref-32","first-page":"734","article-title":"Automatic software refactoring to enhance quality: a review","volume":"10","author":"Khaleel","year":"2024","journal-title":"Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI)"},{"issue":"14","key":"10.7717\/peerj-cs.3642\/ref-33","doi-asserted-by":"publisher","first-page":"21048","DOI":"10.1007\/s11227-024-06265-9","article-title":"Improving accuracy of code smells detection using machine learning with data balancing techniques","volume":"80","author":"Khleel","year":"2024","journal-title":"The Journal of Supercomputing"},{"key":"10.7717\/peerj-cs.3642\/ref-34","article-title":"Empowering automotive software development with LLM-RAG integration: a study on leveraging the RAG-framework for autosar and automotive safety standards and specifications. Master\u2019s thesis, University of Gothenburg","author":"Kieu","year":"2024"},{"key":"10.7717\/peerj-cs.3642\/ref-35","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/978-3-031-79041-6_3","article-title":"Code smell detection using deep learning models to enhance the software quality","author":"Kiran","year":"2024"},{"key":"10.7717\/peerj-cs.3642\/ref-36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2005.11401","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","author":"Lewis","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"10.7717\/peerj-cs.3642\/ref-37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2504.10147","article-title":"A survey of personalization: from rag to agent","author":"Li","year":"2025a"},{"issue":"1","key":"10.7717\/peerj-cs.3642\/ref-38","doi-asserted-by":"publisher","first-page":"107656","DOI":"10.1016\/j.infsof.2024.107656","article-title":"Automated detection of inter-language design smells in multi-language deep learning frameworks","volume":"179","author":"Li","year":"2025b","journal-title":"Information and Software Technology"},{"key":"10.7717\/peerj-cs.3642\/ref-39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2506.10408","article-title":"Reasoning RAG via system 1 or system 2: a survey on reasoning agentic retrieval-augmented generation for industry challenges","author":"Liang","year":"2025"},{"issue":"9","key":"10.7717\/peerj-cs.3642\/ref-40","doi-asserted-by":"publisher","first-page":"1811","DOI":"10.1109\/tse.2019.2936376","article-title":"Deep learning based code smell detection","volume":"47","author":"Liu","year":"2019","journal-title":"IEEE transactions on Software Engineering"},{"issue":"3","key":"10.7717\/peerj-cs.3642\/ref-41","doi-asserted-by":"publisher","first-page":"123483","DOI":"10.1016\/j.eswa.2024.123483","article-title":"Revisiting code smell severity prioritization using learning to rank techniques","volume":"249","author":"Liu","year":"2024c","journal-title":"Expert Systems with Applications"},{"key":"10.7717\/peerj-cs.3642\/ref-42","article-title":"An empirical study on the potential of llms in automated software refactoring. Technical report","author":"Liu","year":"2024a"},{"key":"10.7717\/peerj-cs.3642\/ref-43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2402.10398","article-title":"Prompt learning for multi-label code smell detection: a promising approach","author":"Liu","year":"2024b"},{"key":"10.7717\/peerj-cs.3642\/ref-44","first-page":"444","article-title":"Leveraging prompt-based large language models for code smell detection: a comparative study on the MLCQ dataset","author":"Mesbah","year":"2025"},{"issue":"1","key":"10.7717\/peerj-cs.3642\/ref-45","doi-asserted-by":"publisher","first-page":"80448","DOI":"10.1109\/access.2022.3192514","article-title":"Why is multiclass classification hard?","volume":"10","author":"Moral","year":"2022","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3642\/ref-46","doi-asserted-by":"publisher","first-page":"31335","DOI":"10.1109\/ACCESS.2025.3542566","article-title":"Optimizing pre-trained code embeddings with triplet loss for code smell detection","volume":"13","author":"N\u0131zam","year":"2025","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3642\/ref-47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2504.18956","article-title":"Towards automated detection of inline code comment smells","author":"Oztas","year":"2025"},{"key":"10.7717\/peerj-cs.3642\/ref-48","first-page":"209","article-title":"Do code LLMs understand design patterns?","author":"Pan","year":"2025"},{"key":"10.7717\/peerj-cs.3642\/ref-49","first-page":"462","article-title":"An exploratory study on architectural smell refactoring using large languages models","author":"Pandini","year":"2025"},{"key":"10.7717\/peerj-cs.3642\/ref-50","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.03671","article-title":"Advancing reasoning in large language models: promising methods and approaches","author":"Patil","year":"2025"},{"key":"10.7717\/peerj-cs.3642\/ref-51","first-page":"220","article-title":"Developer-driven code smell prioritization","author":"Pecorelli","year":"2020"},{"key":"10.7717\/peerj-cs.3642\/ref-52","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.18675","article-title":"Agentic large language models, a survey","volume":"84","author":"Plaat","year":"2025","journal-title":"Journal of Artificial Intelligence Research"},{"key":"10.7717\/peerj-cs.3642\/ref-53","first-page":"1","article-title":"Relevance vector machine for code smell detection","author":"Putro","year":"2024"},{"key":"10.7717\/peerj-cs.3642\/ref-54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.12616","article-title":"Improving chain-of-thought reasoning via quasi-symbolic abstractions","author":"Ranaldi","year":"2025"},{"issue":"13","key":"10.7717\/peerj-cs.3642\/ref-55","doi-asserted-by":"publisher","first-page":"7472","DOI":"10.3390\/app15137472","article-title":"An empirical evaluation of ensemble models for python code smell detection","volume":"15","author":"Rao","year":"2025","journal-title":"Applied Sciences"},{"key":"10.7717\/peerj-cs.3642\/ref-56","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.18496","article-title":"AI-powered code review with LLMs: early results","author":"Rasheed","year":"2024"},{"key":"10.7717\/peerj-cs.3642\/ref-57","first-page":"1","article-title":"Agentic retrieval-augmented generation for time series analysis","author":"Ravuru","year":"2024"},{"issue":"3","key":"10.7717\/peerj-cs.3642\/ref-58","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/s10664-021-10110-5","article-title":"Crowdsmelling: a preliminary study on using collective knowledge in code smells detection","volume":"27","author":"Reis","year":"2022","journal-title":"Empirical Software Engineering"},{"key":"10.7717\/peerj-cs.3642\/ref-59","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2012.08842","article-title":"Code smells detection and visualization: a systematic literature review","author":"Reis","year":"2020"},{"key":"10.7717\/peerj-cs.3642\/ref-60","first-page":"354","article-title":"Enhancing code smell detection performance in python programming language: a comparative study","author":"Retnani","year":"2024"},{"issue":"4","key":"10.7717\/peerj-cs.3642\/ref-61","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1561\/1500000019","article-title":"The probabilistic relevance framework: BM25 and beyond","volume":"3","author":"Robertson","year":"2009","journal-title":"Foundations and Trends in Information Retrieval"},{"key":"10.7717\/peerj-cs.3642\/ref-62","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2504.16027","article-title":"Benchmarking LLM for code smells detection: OpenAI GPT-4.0 vs DeepSeek-V3","author":"Sadik","year":"2025"},{"issue":"4","key":"10.7717\/peerj-cs.3642\/ref-63","doi-asserted-by":"publisher","first-page":"e1370","DOI":"10.7717\/peerj-cs.1370","article-title":"Python code smells detection using conventional machine learning models","volume":"9","author":"Sandouka","year":"2023","journal-title":"PeerJ Computer Science"},{"key":"10.7717\/peerj-cs.3642\/ref-64","first-page":"763","article-title":"PyExamine: a comprehensive, un-opinionated smell detection tool for python","author":"Shivashankar","year":"2025"},{"key":"10.7717\/peerj-cs.3642\/ref-65","first-page":"400","article-title":"Detecting code smells using ChatGPT: initial insights","author":"Silva","year":"2024"},{"key":"10.7717\/peerj-cs.3642\/ref-66","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.09136","article-title":"Agentic retrieval-augmented generation: a survey on agentic rag","author":"Singh","year":"2025"},{"issue":"5","key":"10.7717\/peerj-cs.3642\/ref-67","doi-asserted-by":"publisher","first-page":"112101","DOI":"10.1016\/j.jss.2024.112101","article-title":"Do code reviews lead to fewer code smells?","volume":"215","author":"Tuna","year":"2024","journal-title":"Journal of Systems and Software"},{"key":"10.7717\/peerj-cs.3642\/ref-68","first-page":"128","article-title":"Python code smell detection using machine learning","author":"Vatanapakorn","year":"2022"},{"key":"10.7717\/peerj-cs.3642\/ref-69","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/ICSE-NIER66352.2025.00025","article-title":"How propense are large language models at producing code smells? a benchmarking study","author":"Velasco","year":"2025"},{"issue":"4","key":"10.7717\/peerj-cs.3642\/ref-70","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/MS.2025.3549628","article-title":"From code generation to software testing: AI copilot with context-based retrieval-augmented generation","volume":"42","author":"Wang","year":"2025","journal-title":"IEEE Software"},{"key":"10.7717\/peerj-cs.3642\/ref-71","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2109.00859","article-title":"CodeT5: identifier-aware unified pre-trained encoder-decoder models for code understanding and generation","author":"Wang","year":"2021"},{"key":"10.7717\/peerj-cs.3642\/ref-72","first-page":"1345","article-title":"ismell: assembling LLMs with expert toolsets for code smell detection and refactoring","author":"Wu","year":"2024"},{"key":"10.7717\/peerj-cs.3642\/ref-73","first-page":"28489","article-title":"Agentic reasoning: a streamlined framework for enhancing LLM reasoning with agentic tools","author":"Wu","year":"2025"},{"issue":"14","key":"10.7717\/peerj-cs.3642\/ref-74","doi-asserted-by":"publisher","first-page":"6149","DOI":"10.3390\/app14146149","article-title":"Machine learning-based methods for code smell detection: a survey","volume":"14","author":"Yadav","year":"2024","journal-title":"Applied Sciences"},{"issue":"7","key":"10.7717\/peerj-cs.3642\/ref-75","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3717061","article-title":"An empirical study of retrieval-augmented code generation: challenges and opportunities","volume":"34","author":"Yang","year":"2025a","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"issue":"16","key":"10.7717\/peerj-cs.3642\/ref-76","doi-asserted-by":"publisher","first-page":"3127","DOI":"10.3390\/electronics13163127","article-title":"UISGPT: automated mobile ui design smell detection with large language models","volume":"13","author":"Yang","year":"2024","journal-title":"Electronics"},{"key":"10.7717\/peerj-cs.3642\/ref-77","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2507.18515","article-title":"A deep dive into retrieval-augmented generation for code completion: experience on wechat","author":"Yang","year":"2025b"},{"key":"10.7717\/peerj-cs.3642\/ref-78","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.03373","article-title":"Demystifying long chain-of-thought reasoning in LLMs","author":"Yeo","year":"2025"},{"issue":"13s","key":"10.7717\/peerj-cs.3642\/ref-79","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3596908","article-title":"A systematic literature review on the code smells datasets and validation mechanisms","volume":"55","author":"Zakeri-Nasrabadi","year":"2023","journal-title":"ACM Computing Surveys"},{"issue":"3","key":"10.7717\/peerj-cs.3642\/ref-80","doi-asserted-by":"publisher","first-page":"127014","DOI":"10.1016\/j.neucom.2023.127014","article-title":"Code smell detection based on supervised learning models: a survey","volume":"565","author":"Zhang","year":"2024c","journal-title":"Neurocomputing"},{"key":"10.7717\/peerj-cs.3642\/ref-81","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.13801","article-title":"A comprehensive evaluation of parameter-efficient fine-tuning on method-level code smell detection","author":"Zhang","year":"2024a"},{"key":"10.7717\/peerj-cs.3642\/ref-82","doi-asserted-by":"publisher","first-page":"112131","DOI":"10.2139\/ssrn.4693778","article-title":"Data preparation for deep learning based code smell detection: a systematic literature review","volume":"216","author":"Zhang","year":"2024b","journal-title":"Journal of Systems and Software"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3642.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3642.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3642.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3642.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T08:23:32Z","timestamp":1772612612000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3642"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,4]]},"references-count":82,"alternative-id":["10.7717\/peerj-cs.3642"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3642","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,4]]},"article-number":"e3642"}}