{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T14:36:49Z","timestamp":1786113409985,"version":"build-2736575974"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2024YFB3311503"],"award-info":[{"award-number":["2024YFB3311503"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62272445"],"award-info":[{"award-number":["62272445"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Huawei","award":["CCF-HuaweiSE202402"],"award-info":[{"award-number":["CCF-HuaweiSE202402"]}]},{"name":"State Key Laboratory of Complex & Critical Software Environment","award":["CCSE2025ZX-09"],"award-info":[{"award-number":["CCSE2025ZX-09"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IIEEE Trans. Software Eng."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tse.2026.3676295","type":"journal-article","created":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T20:07:23Z","timestamp":1774296443000},"page":"1928-1943","source":"Crossref","is-referenced-by-count":1,"title":["Are They All Good? Evaluating the Quality of CoTs in LLM-Based Code Generation"],"prefix":"10.1109","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6468-9842","authenticated-orcid":false,"given":"Binquan","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University","place":["Beijing, China"],"department":["State Key Laboratory of Complex & Critical Software Environment"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2258-5893","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University","place":["Beijing, China"],"department":["State Key Laboratory of Complex & Critical Software Environment"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2009-5637","authenticated-orcid":false,"given":"Zhiwen","family":"Luo","sequence":"additional","affiliation":[{"name":"Beihang University","place":["Beijing, China"],"department":["School of Software"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4356-8258","authenticated-orcid":false,"given":"Yuxin","family":"Du","sequence":"additional","affiliation":[{"name":"Beihang University","place":["Beijing, China"],"department":["School of Software"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3905-8133","authenticated-orcid":false,"given":"Fang","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University","place":["Beijing, China"],"department":["State Key Laboratory of Complex & Critical Software Environment"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0531-5717","authenticated-orcid":false,"given":"Song","family":"Wang","sequence":"additional","affiliation":[{"name":"York University","place":["Toronto, Canada"],"department":["Lassonde School of Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-7213","authenticated-orcid":false,"given":"Lin","family":"Shi","sequence":"additional","affiliation":[{"name":"Beihang University","place":["Beijing, China"],"department":["School of Software"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Gemini-2.0-flash-thinking-exp-01-21"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635856"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/icsme64153.2025.00043"},{"key":"ref4","article-title":"Chain-of-thought reasoning in the wild is not always faithful","author":"Arcuschin","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-023-10380-1"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref7","article-title":"CodeT: Code generation with generated tests","author":"Chen","year":"2022"},{"key":"ref8","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.426"},{"key":"ref10","article-title":"TestART: Improving LLM-based unit test via co-evolution of automated generation and repair iteration","author":"Gu","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.507"},{"key":"ref13","article-title":"CodeCoT: Tackling code syntax errors in cot reasoning for code generation","author":"Huang","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSR59073.2023.00082"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3672456"},{"key":"ref17","article-title":"SWE-bench: Can language models resolve real-world GitHub issues?","author":"Jimenez","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1613"},{"key":"ref20","first-page":"21314","article-title":"CodeRL: Mastering code generation through pretrained models and deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Le","year":"2022"},{"key":"ref21","article-title":"CodeChain: Towards modular code generation through chain of self-revisions with representative sub-modules","author":"Le","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3690635"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.189"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.673"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.992"},{"key":"ref26","first-page":"669","article-title":"FastFixer: An efficient and effective approach for repairing programming assignments","volume-title":"Proc. 39th IEEE\/ACM Int. Conf. Automated Softw. Eng.","author":"Liu","year":"2024a"},{"key":"ref27","first-page":"21558","article-title":"Is your code generated by ChatGPT really correct? Rigorous evaluation of large language models for code generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu","year":"2024b"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3643674"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2024.3392499"},{"key":"ref31","article-title":"Bridging code semantic and LLMs: Semantic chain-of-thought prompting for code generation","author":"Ma","year":"2023"},{"key":"ref32","first-page":"46534","article-title":"Self-refine: Iterative refinement with self-feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Madaan","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3660810"},{"key":"ref34","article-title":"CodeGen: An open large language model for code with multi-turn program synthesis","author":"Nijkamp","year":"2022"},{"key":"ref35","volume-title":"OpenAI"},{"key":"ref36","article-title":"Mutual reasoning makes smaller LLMs stronger problem-solvers","author":"Qi","year":"2024"},{"key":"ref37","article-title":"Code Llama: Open foundation models for code","author":"Rozi\u00e8re","year":"2023"},{"key":"ref38","article-title":"Amazon CodeWhisperer","year":"2024"},{"key":"ref39","article-title":"Quality and trust in LLM-generated code","author":"Spiess","year":"2024"},{"key":"ref40","first-page":"29106","article-title":"Chain of thoughtlessness? An analysis of cot in planning","volume":"37","author":"Stechly","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.824"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-025-10614-4"},{"key":"ref43","first-page":"117954","article-title":"Code repair with LLMs gives an exploration-exploitation tradeoff","volume":"37","author":"Tang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref44","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref45","first-page":"74952","article-title":"Language models don\u2019t always say what they think: Unfaithful explanations in chain-of-thought prompting","volume":"36","author":"Turpin","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3519665"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3545945.3569830"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3715754"},{"key":"ref50","first-page":"41618","article-title":"Self-evaluation guided beam search for reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"36","author":"Xie","year":"2023"},{"key":"ref51","article-title":"SWE-agent: Agent-computer interfaces enable automated software engineering","author":"Yang","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0517"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.4218\/etrij.2023-0357"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-srw.45"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623322"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3650212.3680384"},{"key":"ref57","article-title":"CortexDebate: Debating sparsely and equally for multi-agent debate","author":"Zhang","year":"2024c"},{"key":"ref58","article-title":"ToolChain*: Efficient action space navigation in large language models with A* search","author":"Zhuang","year":"2023"}],"container-title":["IEEE Transactions on Software Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/32\/11563955\/11450540.pdf?arnumber=11450540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T19:07:03Z","timestamp":1785956823000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11450540\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":58,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tse.2026.3676295","relation":{},"ISSN":["0098-5589","1939-3520","2326-3881"],"issn-type":[{"value":"0098-5589","type":"print"},{"value":"1939-3520","type":"electronic"},{"value":"2326-3881","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}