{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T06:19:10Z","timestamp":1783577950956,"version":"3.55.0"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032306982","type":"print"},{"value":"9783032306999","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:00:00Z","timestamp":1783641600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:00:00Z","timestamp":1783641600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-30699-9_3","type":"book-chapter","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:43:03Z","timestamp":1783575783000},"page":"34-48","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Prompt Optimization for\u00a0LLM Code Generation via\u00a0Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7770-2392","authenticated-orcid":false,"given":"Ali","family":"Mohammadi Esfahani","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9322-0699","authenticated-orcid":false,"given":"Nafiseh","family":"Kahani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8824-1922","authenticated-orcid":false,"given":"Samuel A.","family":"Ajila","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,10]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Ahmad, W.U., Chakraborty, S., Ray, B., Chang, K.W.: Unified pre-training for program understanding and generation. arXiv:2103.06333 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.211"},{"issue":"6","key":"3_CR2","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1007\/s10664-023-10380-1","volume":"28","author":"O Asare","year":"2023","unstructured":"Asare, O., Nagappan, M., Asokan, N.: Is github\u2019s copilot as bad as humans at introducing vulnerabilities in code? Empir. Softw. Eng. 28(6), 129 (2023)","journal-title":"Empir. Softw. Eng."},{"key":"3_CR3","unstructured":"Austin, J., Odena, A., Nye, M., Bosma, et al.: Program synthesis with large language models. arXiv:2108.07732 (2021)"},{"key":"3_CR4","unstructured":"Batorski, P., Kosmala, A., Swoboda, P.: PRL: prompts from reinforcement learning. arXiv:2505.14412 (2025)"},{"key":"3_CR5","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR6","unstructured":"Chen, M., et al.: Evaluating large language models trained on code. arXiv:2107.03374 (2021)"},{"issue":"240","key":"3_CR7","first-page":"1","volume":"24","author":"A Chowdhery","year":"2023","unstructured":"Chowdhery, A., et al.: Palm: scaling language modeling with pathways. J. Mach. Learn. Res. 24(240), 1\u2013113 (2023)","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Deng, M., et al.: Rlprompt: optimizing discrete text prompts with reinforcement learning. arXiv:2205.12548 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.222"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Elnaggar, A., et al.: Codetrans: towards cracking the language of silicon\u2019s code through self-supervised deep learning and high performance computing. arXiv:2104.02443 (2021)","DOI":"10.1101\/2020.07.12.199554"},{"key":"3_CR10","doi-asserted-by":"publisher","unstructured":"Esfahani, A.M., Kahani, N., Ajila, S.A.: Understanding defects in generated codes by language models. In: 2024 34th International Conference on Collaborative Advances in Software and COmputiNg (CASCON), pp. 1\u201310. (2024). https:\/\/doi.org\/10.1109\/CASCON62161.2024.10837857","DOI":"10.1109\/CASCON62161.2024.10837857"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Feng, Z., et al.: Codebert: a pre-trained model for programming and natural languages. arXiv:2002.08155 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"3_CR12","unstructured":"Fernando, C., Banarse, D., Michalewski, H., Osindero, S., Rockt\u00e4schel, T.: Promptbreeder: self-referential self-improvement via prompt evolution. arXiv:2309.16797 (2023)"},{"key":"3_CR13","unstructured":"Fried, D., et al.: Incoder: a generative model for code infilling and synthesis. arXiv:2204.05999 (2022)"},{"key":"3_CR14","unstructured":"Guo, D., et al.: Graphcodebert: pre-training code representations with data flow. arXiv:2009.08366 (2020)"},{"key":"3_CR15","unstructured":"Guo, Q., et al.: Evoprompt: connecting LLMs with evolutionary algorithms yields powerful prompt optimizers. In: International Conference on Learning Representations (ICLR) (2024). https:\/\/arxiv.org\/abs\/2309.08532"},{"key":"3_CR16","unstructured":"Hendrycks, D., et al.: Measuring coding challenge competence with apps. arXiv:2105.09938 (2021)"},{"key":"3_CR17","unstructured":"Holden, D., Kahani, N.: Code linting using language models. arXiv preprint arXiv:2406.19508 (2024)"},{"key":"3_CR18","doi-asserted-by":"crossref","unstructured":"Hou, X., Zhao, Y., Liu, Y., et al.: Large language models for software engineering: a systematic literature review (2024)","DOI":"10.1145\/3695988"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Kong, W., Hombaiah, S.A., Zhang, M., Mei, Q., Bendersky, M.: Prewrite: prompt rewriting with reinforcement learning. In: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) (2024)","DOI":"10.18653\/v1\/2024.acl-short.54"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Kwon, M., Kim, G., Kim, J., Lee, H., Kim, J.: Stableprompt: automatic prompt tuning using reinforcement learning for large language models. arXiv:2410.07652 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.551"},{"key":"3_CR21","unstructured":"Li, C., et al.: Chain of code: reasoning with a language model-augmented code emulator. arXiv:2312.04474 (2023)"},{"key":"3_CR22","doi-asserted-by":"publisher","first-page":"21558","DOI":"10.52202\/075280-0943","volume":"36","author":"J Liu","year":"2023","unstructured":"Liu, J., Xia, C.S., Wang, Y., Zhang, L.: Is your code generated by chatgpt really correct? Rigorous evaluation of large language models for code generation. Adv. Neural. Inf. Process. Syst. 36, 21558\u201321572 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR23","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1109\/TSE.1976.233837","volume":"4","author":"TJ McCabe","year":"1976","unstructured":"McCabe, T.J.: A complexity measure. IEEE Trans. Software Eng. 4, 308\u2013320 (1976)","journal-title":"IEEE Trans. Software Eng."},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Mohammadkhani, A.H., Tantithamthavorn, C., Hemmatif, H.: Explaining transformer-based code models: what do they learn? When they do not work? pp. 96\u2013106 (2023)","DOI":"10.1109\/SCAM59687.2023.00020"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. In: Advances in Neural Information Processing Systems, vol. 35, pp. 27730\u201327744 (2022)","DOI":"10.52202\/068431-2011"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-bert: sentence embeddings using siamese bert-networks. In: EMNLP (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"3_CR27","unstructured":"Roziere, B., Gehring, J., Gloeckle, et al.: Code llama: open foundation models for code. arXiv:2308.12950 (2023)"},{"key":"3_CR28","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., et al.: Proximal policy optimization algorithms (2017)"},{"key":"3_CR29","doi-asserted-by":"publisher","first-page":"8634","DOI":"10.52202\/075280-0377","volume":"36","author":"N Shinn","year":"2023","unstructured":"Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K., Yao, S.: Reflexion: language agents with verbal reinforcement learning. Adv. Neural. Inf. Process. Syst. 36, 8634\u20138652 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3_CR30","unstructured":"Taherkhani, H., Sepidband, M., et al.: Epic: cost-effective search-based prompt engineering of LLMs for code generation. arXiv:2408.11198 (2024)"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Tambon, F., Dakhel, A.M., Nikanjam, A., Khomh, F., Desmarais, M.C., Antoniol, G.: Bugs in large language models generated code. arXiv:2403.08937 (2024)","DOI":"10.1007\/s10664-025-10614-4"},{"key":"3_CR32","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models. arXiv:2302.13971 (2023)"},{"key":"3_CR33","doi-asserted-by":"crossref","unstructured":"Wang, J., Huang, Y., Chen, C., Liu, Z., Wang, S., Wang, Q.: Software testing with large language models: survey, landscape, and vision (2024)","DOI":"10.1109\/TSE.2024.3368208"},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Wang, Y., Le, H., Gotmare, A.D., Bui, N.D.Q., Li, J., Hoi, S.C.H.: Codet5+: open code large language models for code understanding and generation (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.68"},{"key":"3_CR35","unstructured":"Yang, C., et al.: Large language models as optimizers. arXiv:2309.03409 (2023)"},{"key":"3_CR36","unstructured":"Zhang, Z., et al.: Unifying the perspectives of NLP and software engineering: a survey on language models for code. arXiv:2311.07989 (2023)"},{"key":"3_CR37","unstructured":"Zhao, W.X., Zhou, K., Li, et al.: A survey of large language models. arXiv:2303.18223 (2023)"},{"key":"3_CR38","doi-asserted-by":"crossref","unstructured":"Zhong, L., Wang, Z., Shang, J.: Debug like a human: a large language model debugger via verifying runtime execution step-by-step. arXiv:2402.16906 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.49"},{"key":"3_CR39","unstructured":"Zhu, Q., et al.: Deepseek-coder-v2: breaking the barrier of closed-source models in code intelligence. arXiv:2406.11931 (2024)"}],"container-title":["Lecture Notes in Computer Science","Search-Based Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-30699-9_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:43:07Z","timestamp":1783575787000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-30699-9_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,10]]},"ISBN":["9783032306982","9783032306999"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-30699-9_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,10]]},"assertion":[{"value":"10 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SSBSE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Search Based Software Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Montreal, QC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ssbse2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conf.researchr.org\/home\/ssbse-2026","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}