{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:42:19Z","timestamp":1784302939920,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T00:00:00Z","timestamp":1775952000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,12]]},"DOI":"10.1145\/3786582.3786835","type":"proceedings-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T11:52:47Z","timestamp":1783511567000},"page":"181-185","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Specification and Detection of LLM Code Smells"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3007-7080","authenticated-orcid":false,"given":"Brahim","family":"Mahmoudi","sequence":"first","affiliation":[{"name":"\u00c9cole de technologie sup\u00e9rieure, Montr\u00e9al, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7464-6659","authenticated-orcid":false,"given":"Zacharie","family":"Chenail-Larcher","sequence":"additional","affiliation":[{"name":"\u00c9cole de technologie sup\u00e9rieure (\u00c9TS), Montr\u00e9al, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9252-9937","authenticated-orcid":false,"given":"Naouel","family":"Moha","sequence":"additional","affiliation":[{"name":"\u00c9cole de Technologie Sup\u00e9rieure de Montr\u00e9al, Montr\u00e9al, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9985-9808","authenticated-orcid":false,"given":"Quentin","family":"Sti\u00e9venart","sequence":"additional","affiliation":[{"name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al, Montr\u00e9al, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1030-5388","authenticated-orcid":false,"given":"Florent","family":"Avellaneda","sequence":"additional","affiliation":[{"name":"Universit\u00e9 du Qu\u00e9bec \u00e0 Montr\u00e9al, Montr\u00e9al, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,8]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Amey Agrawal Nitin Kedia Anmol Agarwal Jayashree Mohan Nipun Kwatra Souvik Kundu Ramachandran Ramjee and Alexey Tumanov. 2025. On Evaluating Performance of LLM Inference Serving Systems. arxiv:https:\/\/arXiv.org\/abs\/2507.09019\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2507.09019"},{"key":"e_1_3_3_1_3_2","volume-title":"Timeouts, retries and backoff","author":"Services Amazon Web","year":"2025","unstructured":"Amazon Web Services. 2025. Timeouts, retries and backoff. https:\/\/aws.amazon.com\/fr\/builders-library\/timeouts-retries-and-backoff-with-jitter"},{"key":"e_1_3_3_1_4_2","volume-title":"Claude Documentation (API, Models)","year":"2025","unstructured":"Anthropic. 2025. Claude Documentation (API, Models). https:\/\/docs.claude.com\/"},{"key":"e_1_3_3_1_5_2","volume-title":"structured-logprobs","year":"2025","unstructured":"arena-ai. 2025. structured-logprobs. https:\/\/github.com\/arena-ai\/structured-logprobs OS library: enhances OpenAI Structured Outputs with token logprobs."},{"key":"e_1_3_3_1_6_2","volume-title":"Replication_Package_LLM_code_smells","author":"Brahim Mahmoudi","year":"2025","unstructured":"Mahmoudi Brahim and Chenail-larcher Zacharie. 2025. Replication_Package_LLM_code_smells. https:\/\/github.com\/Brahim-Mahmoudi\/SpecDetect4LLM_ICSE"},{"key":"e_1_3_3_1_7_2","unstructured":"Alessio Bucaioni Martin Weyssow Junda He Yunbo Lyu and David Lo. 2025. A Functional Software Reference Architecture for LLM-Integrated Systems. arxiv:https:\/\/arXiv.org\/abs\/2501.12904\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2501.12904"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","unstructured":"Silvio\u00a0G. Carvalho Maur\u00edcio Aniche Jo\u00e3o Ver\u00edssimo Alessandro Garcia Vitor Alves and Rohit Gheyi. 2019. An empirical catalog of code smells for the presentation layer of Android apps. Empirical Software Engineering 24 6 (dec 2019) 3546\u20133586. 10.1007\/s10664-019-09768-9","DOI":"10.1007\/s10664-019-09768-9"},{"key":"e_1_3_3_1_9_2","unstructured":"Mert Cemri Melissa\u00a0Z. Pan Shuyi Yang Lakshya\u00a0A. Agrawal Bhavya Chopra Rishabh Tiwari Kurt Keutzer Aditya Parameswaran Dan Klein Kannan Ramchandran Matei Zaharia Joseph\u00a0E. Gonzalez and Ion Stoica. 2025. Why Do Multi-Agent LLM Systems Fail? arxiv:https:\/\/arXiv.org\/abs\/2503.13657\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2503.13657"},{"key":"e_1_3_3_1_10_2","unstructured":"Zixi Chen Yinyu Ye and Zijie Zhou. 2025. Adaptively Robust LLM Inference Optimization under Prediction Uncertainty. arxiv:https:\/\/arXiv.org\/abs\/2508.14544\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2508.14544"},{"key":"e_1_3_3_1_11_2","volume-title":"System Messages: Best Practices, Real-world Experiments & Prompt Injection Protectors","author":"Cleary Dan","year":"2025","unstructured":"Dan Cleary. 2025. System Messages: Best Practices, Real-world Experiments & Prompt Injection Protectors. https:\/\/www.prompthub.us\/blog\/everything-system-messages-how-to-use-them-real-world-experiments-prompt-injection-protectors PromptHub Blog."},{"key":"e_1_3_3_1_12_2","volume-title":"What is the use case of System role","year":"2023","unstructured":"cyz3a5c0v1. 2023. What is the use case of System role. https:\/\/stackoverflow.com\/questions\/76272624\/what-is-the-use-case-of-system-role"},{"key":"e_1_3_3_1_13_2","volume-title":"A Practical Guide on Structuring LLM Outputs with Pydantic","author":"Service Developer","year":"2025","unstructured":"Developer Service. 2025. A Practical Guide on Structuring LLM Outputs with Pydantic. https:\/\/dev.to\/devasservice\/a-practical-guide-on-structuring-llm-outputs-with-pydantic-50b4"},{"key":"e_1_3_3_1_14_2","unstructured":"Ali\u00a0Mohammadi Esfahani Nafiseh Kahani and Samuel\u00a0A. Ajila. 2024. Understanding Defects in Generated Codes by Language Models. arxiv:https:\/\/arXiv.org\/abs\/2408.13372\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2408.13372"},{"key":"e_1_3_3_1_15_2","volume-title":"Refactoring: improving the design of existing code","author":"Fowler Martin","year":"1999","unstructured":"Martin Fowler, Kent Beck, John Brant, William Opdyke, and Don Roberts. 1999. Refactoring: improving the design of existing code. Addison-Wesley Longman Publishing Co., Inc., USA."},{"key":"e_1_3_3_1_16_2","volume-title":"Gemini API - Google AI for Developers","year":"2025","unstructured":"Google. 2025. Gemini API - Google AI for Developers. https:\/\/ai.google.dev\/"},{"key":"e_1_3_3_1_17_2","volume-title":"Quotas and limits - BigQuery","author":"Cloud Google","year":"2025","unstructured":"Google Cloud. 2025. Quotas and limits - BigQuery. https:\/\/cloud.google.com\/bigquery\/quotas"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","unstructured":"Tingxu Han Zhenting Wang Chunrong Fang Shunyuan Zhao Shiqing Ma and Ziang Chen. 2025. Token-Budget-Aware LLM Reasoning. 24842\u201324855\u00a0pages. 10.18653\/v1\/2025.findings-acl.1274","DOI":"10.18653\/v1\/2025.findings-acl.1274"},{"key":"e_1_3_3_1_19_2","volume-title":"Transformers Documentation (Generation, Chat Templates, Model Revisions)","author":"Face Hugging","year":"2025","unstructured":"Hugging Face. 2025. Transformers Documentation (Generation, Chat Templates, Model Revisions). https:\/\/huggingface.co\/docs\/transformers"},{"key":"e_1_3_3_1_20_2","unstructured":"Minbyul Jeong Jungho Cho Minsoo Khang Dawoon Jung and Teakgyu Hong. 2025. System Message Generation for User Preferences using Open-Source Models. arxiv:https:\/\/arXiv.org\/abs\/2502.11330\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2502.11330"},{"key":"e_1_3_3_1_21_2","unstructured":"Zixuan Ke Fangkai Jiao Yifei Ming Xuan-Phi Nguyen Austin Xu Do\u00a0Xuan Long Minzhi Li Chengwei Qin Peifeng Wang Silvio Savarese Caiming Xiong and Shafiq Joty. 2025. A Survey of Frontiers in LLM Reasoning: Inference Scaling Learning to Reason and Agentic Systems. arxiv:https:\/\/arXiv.org\/abs\/2504.09037\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2504.09037"},{"key":"e_1_3_3_1_22_2","volume-title":"Enforcing JSON Outputs in Commercial LLMs","author":"Kharitonov Daniel","year":"2024","unstructured":"Daniel Kharitonov. 2024. Enforcing JSON Outputs in Commercial LLMs. https:\/\/medium.com\/data-science\/enforcing-json-outputs-in-commercial-llms-3db590b9b3c8 Towards Data Science."},{"key":"e_1_3_3_1_23_2","unstructured":"Aisha Khatun. 2024. Uncovering the Reliability and Consistency of AI Language Models: A Systematic Study. Ph.\u00a0D. Dissertation. University of Waterloo. https:\/\/uwspace.uwaterloo.ca\/items\/e01e11a6-e033-4f6a-85c6-849fba74e039"},{"key":"e_1_3_3_1_24_2","volume-title":"Guidelines for performing Systematic Literature Reviews in Software Engineering","author":"Kitchenham Barbara","year":"2007","unstructured":"Barbara Kitchenham and Stuart Charters. 2007. Guidelines for performing Systematic Literature Reviews in Software Engineering. Technical Report EBSE-2007-01. EBSE 2007. https:\/\/www.elsevier.com\/__data\/promis_misc\/525444systematicreviewsguide.pdf"},{"key":"e_1_3_3_1_25_2","unstructured":"Pierre Le\u00a0Jeune Jiaen Liu Luca Rossi and Matteo Dora. 2025. RealHarm: A Collection of Real-World Language Model Application Failures. 87\u2013100\u00a0pages."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","unstructured":"Michael\u00a0Xieyang Liu Frederick Liu Alexander\u00a0J. Fiannaca Terry Koo Lucas Dixon Michael Terry and Carrie\u00a0J. Cai. 2024. We Need Structured Output: Towards User-centered Constraints on Large Language Model Output. 10.1145\/3613905.3650756","DOI":"10.1145\/3613905.3650756"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","unstructured":"Brahim Mahmoudi Naouel Moha Quentin Stievenert and Florent Avellaneda. 2025. AI-Specific Code Smells: From Specification to Detection. arxiv:https:\/\/arXiv.org\/abs\/2509.20491\u00a0[cs.SE] 10.48550\/arXiv.2509.20491","DOI":"10.48550\/arXiv.2509.20491"},{"key":"e_1_3_3_1_28_2","volume-title":"PydanticOutputParser has high chance failing when completion contains new line #3709","year":"2023","unstructured":"mariafilippa. 2023. PydanticOutputParser has high chance failing when completion contains new line #3709. https:\/\/github.com\/hwchase17\/langchain\/issues\/3709 GitHub issue."},{"key":"e_1_3_3_1_29_2","volume-title":"Azure OpenAI - Documentation (Quotas, Structured Outputs, How-To)","author":"Learn Microsoft","year":"2025","unstructured":"Microsoft Learn. 2025. Azure OpenAI - Documentation (Quotas, Structured Outputs, How-To). https:\/\/learn.microsoft.com\/en-us\/azure\/ai-foundry\/openai\/"},{"key":"e_1_3_3_1_30_2","volume-title":"Design to Support Foundation Model Life Cycles","author":"Learn Microsoft","year":"2025","unstructured":"Microsoft Learn. 2025. Design to Support Foundation Model Life Cycles. https:\/\/learn.microsoft.com\/en-us\/azure\/architecture\/ai-ml\/guide\/manage-foundation-models-lifecycle"},{"key":"e_1_3_3_1_31_2","unstructured":"Nguyen\u00a0Nhat Minh Andrew Baker Clement Neo Allen\u00a0G. Roush Andreas Kirsch and Ravid Shwartz-Ziv. 2025. Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs."},{"key":"e_1_3_3_1_32_2","volume-title":"How To Ensure LLM Output Adheres to a JSON Schema","year":"2024","unstructured":"Modelmetry. 2024. How To Ensure LLM Output Adheres to a JSON Schema. https:\/\/modelmetry.com\/blog\/how-to-ensure-llm-output-adheres-to-a-json-schema"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","unstructured":"Jo\u00e3o\u00a0Eduardo Montandon Luciana\u00a0Lourdes Silva Cristiano Politowski Daniel Prates Arthur de Brito\u00a0Bonif\u00e1cio and Ghizlane\u00a0El Boussaidi. 2025. Unboxing Default Argument Breaking Changes in Data Science Libraries. arxiv:https:\/\/arXiv.org\/abs\/2408.05129\u00a0[cs.SE] 10.48550\/arXiv.2408.05129JSS.","DOI":"10.48550\/arXiv.2408.05129"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","unstructured":"Masumi Morishige and Ryo Koshihara. 2025. Ensuring Reproducibility in Generative AI Systems for General Use Cases: A Framework for Regression Testing and Open Datasets. arxiv:https:\/\/arXiv.org\/abs\/2505.0285410.48550\/arXiv.2505.02854","DOI":"10.48550\/arXiv.2505.02854"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","unstructured":"Anna Neumann Elisabeth Kirsten Muhammad\u00a0Bilal Zafar and Jatinder Singh. 2025. Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs). 573\u2013598\u00a0pages. 10.1145\/3715275.3732038","DOI":"10.1145\/3715275.3732038"},{"key":"e_1_3_3_1_36_2","unstructured":"Kaiwen Ning Jiachi Chen Jingwen Zhang Wei Li Zexu Wang Yuming Feng Weizhe Zhang and Zibin Zheng. 2024. Defining and Detecting the Defects of the Large Language Model-based Autonomous Agents. arxiv:https:\/\/arXiv.org\/abs\/2412.18371\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2412.18371"},{"key":"e_1_3_3_1_37_2","volume-title":"Modelfile: Valid parameters and values","year":"2025","unstructured":"Ollama. 2025. Modelfile: Valid parameters and values. https:\/\/github.com\/ollama\/ollama\/blob\/main\/docs\/modelfile.md#valid-parameters-and-values"},{"key":"e_1_3_3_1_38_2","volume-title":"API Reference - Structured model outputs","year":"2025","unstructured":"OpenAI. 2025. API Reference - Structured model outputs. https:\/\/platform.openai.com\/docs\/guides\/structured-outputs"},{"key":"e_1_3_3_1_39_2","volume-title":"OpenAI Platform Documentation","year":"2025","unstructured":"OpenAI. 2025. OpenAI Platform Documentation. https:\/\/platform.openai.com\/docs"},{"key":"e_1_3_3_1_40_2","volume-title":"openai-python","year":"2025","unstructured":"OpenAI. 2025. openai-python. https:\/\/github.com\/openai\/openai-python"},{"key":"e_1_3_3_1_41_2","volume-title":"OpenRouter.ai - One API for Any Model","year":"2025","unstructured":"OpenRouter. 2025. OpenRouter.ai - One API for Any Model. https:\/\/openrouter.ai\/"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","unstructured":"Frank Reyes Yogya Gamage Gabriel Skoglund Benoit Baudry and Martin Monperrus. 2024. BUMP: A Benchmark of Reproducible Breaking Dependency Updates. arxiv:https:\/\/arXiv.org\/abs\/2401.0990610.48550\/arXiv.2401.09906","DOI":"10.48550\/arXiv.2401.09906"},{"key":"e_1_3_3_1_43_2","unstructured":"Krishna Ronanki Beatriz Cabrero-Daniel and Christian Berger. 2024. Prompt Smells: An Omen for Undesirable Generative AI Outputs. arxiv:https:\/\/arXiv.org\/abs\/2401.12611\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2401.12611"},{"key":"e_1_3_3_1_44_2","unstructured":"Yuchen Shao Yuheng Huang Jiawei Shen Lei Ma Ting Su and Chengcheng Wan. 2025. Are LLMs Correctly Integrated into Software Systems? arxiv:https:\/\/arXiv.org\/abs\/2407.05138\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2407.05138"},{"key":"e_1_3_3_1_45_2","unstructured":"Haoye Tian Chong Wang BoYang Yang Lyuye Zhang and Yang Liu. 2025. A Taxonomy of Prompt Defects in LLM Systems. arxiv:https:\/\/arXiv.org\/abs\/2509.14404\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2509.14404"},{"key":"e_1_3_3_1_46_2","volume-title":"LLM Temperature: How It Works and When You Should Use It","author":"AI Vellum","year":"2025","unstructured":"Vellum AI. 2025. LLM Temperature: How It Works and When You Should Use It. https:\/\/www.vellum.ai\/llm-parameters\/temperature"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","unstructured":"Daniel Venturini Filipe\u00a0Roseiro Cogo Ivanilton Polato Marco\u00a0A. Gerosa and Igor\u00a0Scaliante Wiese. 2023. I Depended on You and You Broke Me: An Empirical Study of Manifesting Breaking Changes in Client Packages. arxiv:https:\/\/arXiv.org\/abs\/2301.0456310.48550\/arXiv.2301.04563TOSEM 2023.","DOI":"10.48550\/arXiv.2301.04563"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"crossref","unstructured":"Greg Wilson D.\u00a0A. Aruliah C.\u00a0Titus Brown Neil\u00a0P. Chue\u00a0Hong Matt Davis Richard\u00a0T. Guy Steven H.\u00a0D. Haddock Kathryn\u00a0D. Huff Ian\u00a0M. Mitchell Mark\u00a0D. Plumbley Ben Waugh Ethan\u00a0P. White and Paul Wilson. 2014. Best Practices for Scientific Computing. PLOS Biology 12 1 (2014) e1001745.","DOI":"10.1371\/journal.pbio.1001745"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","unstructured":"Cailin Winston and Ren\u00e9 Just. 2025. A Taxonomy of Failures in Tool-Augmented LLMs. 125\u2013135\u00a0pages. 10.1109\/AST66626.2025.00019","DOI":"10.1109\/AST66626.2025.00019"},{"key":"e_1_3_3_1_50_2","volume-title":"How to Validate the Output of LLM-Based Products","author":"Wyman Matt","year":"2024","unstructured":"Matt Wyman and Sarah Barber. 2024. How to Validate the Output of LLM-Based Products. https:\/\/okareo.com\/blog\/posts\/validate-llm-output"},{"key":"e_1_3_3_1_51_2","unstructured":"Zhiqiu Xia Lang Zhu Bingzhe Li Feng Chen Qiannan Li Chunhua Liao Feiyi Wang and Hang Liu. 2025. Analyzing 16 193 LLM Papers for Fun and Profits. arxiv:https:\/\/arXiv.org\/abs\/2504.08619\u00a0[cs.DL] https:\/\/arxiv.org\/abs\/2504.08619"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","unstructured":"Wenli Yang Lilian Some Michael Bain and Byeong Kang. 2025. A comprehensive survey on integrating large language models with knowledge-based methods. Knowledge-Based Systems 318 (2025) 113503. 10.1016\/j.knosys.2025.113503","DOI":"10.1016\/j.knosys.2025.113503"},{"key":"e_1_3_3_1_53_2","unstructured":"Haiyin Zhang Lu\u00eds Cruz and Arie van Deursen. 2022. Code Smells for ML Applications. arxiv:https:\/\/arXiv.org\/abs\/2203.13746\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2203.13746"},{"key":"e_1_3_3_1_54_2","unstructured":"Terry\u00a0Yue Zhuo Junda He Jiamou Sun Zhenchang Xing David Lo John Grundy and Xiaoning Du. 2025. Identifying and Mitigating API Misuse in Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2503.22821\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2503.22821"}],"event":{"name":"ICSE-NIER '26: 2026 IEEE\/ACM 48th International Conference on Software Engineering","location":"Rio de Janeiro Brazil","acronym":"ICSE-NIER '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the IEEE\/ACM 48th International Conference on Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3786582.3786835","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T11:53:06Z","timestamp":1783511586000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786582.3786835"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":53,"alternative-id":["10.1145\/3786582.3786835","10.1145\/3786582"],"URL":"https:\/\/doi.org\/10.1145\/3786582.3786835","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-07-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}