{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T01:18:47Z","timestamp":1760059127060,"version":"build-2065373602"},"reference-count":55,"publisher":"Association for Computing Machinery (ACM)","issue":"OOPSLA2","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Program. Lang."],"published-print":{"date-parts":[[2025,10,9]]},"abstract":"<jats:p>\n            Software development is shifting from traditional programming to\n            <jats:italic toggle=\"yes\">AI-integrated<\/jats:italic>\n            applications that leverage generative AI and large language models (LLMs) during runtime. However, integrating LLMs remains complex, requiring developers to manually craft prompts and process outputs. Existing tools attempt to assist with prompt engineering, but often introduce additional complexity.\n          <\/jats:p>\n          <jats:p>\n            This paper presents\n            <jats:bold>Meaning-Typed Programming (MTP)<\/jats:bold>\n            , a novel paradigm that abstracts LLM integration through intuitive language-level constructs. By leveraging the inherent semantic richness of code, MTP automates prompt generation and response handling without additional developer effort. We introduce the\n            <jats:bold>(1) by<\/jats:bold>\n            operator for seamless LLM invocation,\n            <jats:bold>(2) MT-IR<\/jats:bold>\n            , a meaning-based intermediate representation for semantic extraction, and\n            <jats:bold>(3) MT-Runtime<\/jats:bold>\n            , an automated system for managing LLM interactions. We implement MTP in\n            <jats:bold>Jac<\/jats:bold>\n            , a programming language that supersets Python, and find that MTP significantly reduces coding complexity while maintaining accuracy and efficiency. MTP significantly reduces development complexity, lines of code modifications needed, and costs while improving run-time performance and maintaining or exceeding the accuracy of existing approaches. Our user study shows that developers using MTP completed tasks 3.2\u00d7 faster with 45% fewer lines of code compared to existing frameworks. Moreover,  demonstrates resilience even when up to 50% of naming conventions are degraded, demonstrating robustness to suboptimal code.  is developed as part of the Jaseci open-source project, and is available under the module\n            <jats:bold>byLLM<\/jats:bold>\n            .\n          <\/jats:p>","DOI":"10.1145\/3763092","type":"journal-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T08:51:31Z","timestamp":1759999891000},"page":"1176-1204","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MTP: A Meaning-Typed Language Abstraction for AI-Integrated Programming"],"prefix":"10.1145","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4320-8280","authenticated-orcid":false,"given":"Jayanaka L.","family":"Dantanarayana","sequence":"first","affiliation":[{"name":"University of Michigan, Ann Arbor, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5964-3655","authenticated-orcid":false,"given":"Yiping","family":"Kang","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4657-4947","authenticated-orcid":false,"given":"Kugesan","family":"Sivasothynathan","sequence":"additional","affiliation":[{"name":"Jaseci Labs, Ann Arbor, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8741-3155","authenticated-orcid":false,"given":"Christopher","family":"Clarke","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4812-6303","authenticated-orcid":false,"given":"Baichuan","family":"Li","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4911-7597","authenticated-orcid":false,"given":"Savini","family":"Kashmira","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8347-1811","authenticated-orcid":false,"given":"Krisztian","family":"Flautner","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5609-7775","authenticated-orcid":false,"given":"Lingjia","family":"Tang","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7029-5292","authenticated-orcid":false,"given":"Jason","family":"Mars","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,9]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3617232.3624849"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00051"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591300"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651330"},{"key":"e_1_2_1_6_1","volume-title":"TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. https:\/\/api.semanticscholar.org\/CorpusID:52939079","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Q. Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. 2018. TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. https:\/\/api.semanticscholar.org\/CorpusID:52939079"},{"key":"e_1_2_1_7_1","volume-title":"Serving Heterogeneous Machine Learning Models on Multi-GPU Servers with Spatio-Temporal Sharing. In 2022 USENIX Annual Technical Conference (USENIX ATC 22)","author":"Choi Seungbeom","year":"2022","unstructured":"Seungbeom Choi, Sunho Lee, Yeonjae Kim, Jongse Park, Youngjin Kwon, and Jaehyuk Huh. 2022. Serving Heterogeneous Machine Learning Models on Multi-GPU Servers with Spatio-Temporal Sharing. In 2022 USENIX Annual Technical Conference (USENIX ATC 22). USENIX Association, Carlsbad, CA. 199\u2013216. isbn:978-1-939133-29-53 https:\/\/www.usenix.org\/conference\/atc22\/presentation\/choi-seungbeom"},{"key":"e_1_2_1_8_1","volume-title":"Training Verifiers to Solve Math Word Problems. ArXiv, abs\/2110.14168","author":"Cobbe Karl","year":"2021","unstructured":"Karl Cobbe, Vineet Kosaraju, Mo Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021. Training Verifiers to Solve Math Word Problems. ArXiv, abs\/2110.14168 (2021), https:\/\/api.semanticscholar.org\/CorpusID:239998651"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Jayanaka Lakindu Dantanarayana Yiping Kang Kugesan Sivasothynathan Christopher Clarke Baichuan Li Savini Kashmira Krisztian Flautner Lingjia Tang and Jason Mars. 2025. Jayanaka-98\/mtllm-oopsla2025: OOPSLA 2025 Artifact. https:\/\/doi.org\/10.5281\/zenodo.16929189 10.5281\/zenodo.16929189","DOI":"10.5281\/zenodo.16929189"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640367"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.365"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640365"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651383"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00050"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/3488766.3488792"},{"key":"e_1_2_1_17_1","unstructured":"Omar Khattab Arnav Singhvi Paridhi Maheshwari Zhiyuan Zhang Keshav Santhanam Sri Vardhamanan A Saiful Haq Ashutosh Sharma Thomas T. Joshi Hanna Moazam Heather Miller Matei Zaharia and Christopher Potts. 2024. DSPy: Compiling Declarative Language Model Calls into State-of-the-Art Pipelines. https:\/\/openreview.net\/forum?id=sY5N0zY5Od"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3623278.3624753"},{"key":"e_1_2_1_19_1","unstructured":"Jaseci Labs. 2024. Jaclang Pypi Package. https:\/\/pypi.org\/project\/jaclang\/ Accessed: 2024-10-18"},{"key":"e_1_2_1_20_1","unstructured":"Jaseci Labs. 2024. Jaseci Github Repo. https:\/\/github.com\/Jaseci-Labs\/jaseci Accessed: 2024-10-18"},{"key":"e_1_2_1_21_1","unstructured":"Langchain. 2024. Langchain. https:\/\/github.com\/langchain-ai\/langchain Accessed: 2024-10-18"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370308"},{"key":"e_1_2_1_23_1","volume-title":"Freund","author":"Levin Kyla H.","year":"2025","unstructured":"Kyla H. Levin, Kyle Gwilt, Emery D. Berger, and Stephen N. Freund. 2025. Effective LLM-Driven Code Generation with Pythoness. arxiv:2501.02138. arxiv:2501.02138"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591280"},{"key":"e_1_2_1_25_1","volume-title":"Advances in Neural Information Processing Systems","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual Instruction Tuning. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.). 36, Curran Associates, Inc., 34892\u201334916. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/6dcf277ea32ce3288914faf369fe6de0-Paper-Conference.pdf"},{"key":"e_1_2_1_26_1","unstructured":"Jerry Liu. 2022. LlamaIndex. https:\/\/docs.llamaindex.ai\/en\/stable\/"},{"key":"e_1_2_1_27_1","unstructured":"Jason Mars. 2025. Extending Object Spatial Semantics for Scale Agnostic Programming. arxiv:2504.03109. arxiv:2504.03109"},{"key":"e_1_2_1_28_1","unstructured":"Jason Mars. 2025. Object-Spatial Programming. arxiv:2503.15812. arxiv:2503.15812"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2023.3274038"},{"key":"e_1_2_1_30_1","volume-title":"Beginning game development with Python and Pygame: from novice to professional","author":"McGugan Will","unstructured":"Will McGugan. 2007. Beginning game development with Python and Pygame: from novice to professional. Apress."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651335"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640411"},{"key":"e_1_2_1_33_1","unstructured":"Microsoft. [n. d.]. TypeChat: Helps get well-typed responses from language models to build pragmatic natural language interfaces. https:\/\/microsoft.github.io\/TypeChat Accessed: 2025-08-21"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454083"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640383"},{"key":"e_1_2_1_36_1","unstructured":"OpenAI. 2024. OpenAI API Pricing. https:\/\/openai.com\/api\/pricing\/ Accessed: 2024-10-18"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3623278.3624761"},{"key":"e_1_2_1_38_1","unstructured":"Python Software Foundation. 2024. The Python Standard Library: cProfile \u2014 Profile Module. https:\/\/docs.python.org\/3\/library\/profile.html##module-cProfile Accessed: 2024-10-19"},{"key":"e_1_2_1_39_1","volume-title":"Glow: Graph Lowering Compiler Techniques for Neural Networks. arxiv:1805.00907. arxiv:1805.00907","author":"Rotem Nadav","year":"2019","unstructured":"Nadav Rotem, Jordan Fix, Saleem Abdulrasool, Garret Catron, Summer Deng, Roman Dzhabarov, Nick Gibson, James Hegeman, Meghan Lele, Roman Levenstein, Jack Montgomery, Bert Maher, Satish Nadathur, Jakob Olesen, Jongsoo Park, Artem Rakhov, Misha Smelyanskiy, and Man Wang. 2019. Glow: Graph Lowering Compiler Techniques for Neural Networks. arxiv:1805.00907. arxiv:1805.00907"},{"key":"e_1_2_1_40_1","volume-title":"Shraddha Barke, and Benjamin Zorn.","author":"Sharma Reshabh K","year":"2025","unstructured":"Reshabh K Sharma, Jonathan De Halleux, Shraddha Barke, and Benjamin Zorn. 2025. PromptPex: Automatic Test Generation for Language Model Prompts. arxiv:2503.05070. arxiv:2503.05070"},{"key":"e_1_2_1_41_1","unstructured":"ShawCode. 2021. Pygame RPG Tutorial. YouTube. https:\/\/www.youtube.com\/playlist?list=PLkkm3wcQHjT7gn81Wn-e78cAyhwBW3FIc Accessed: 2024-09-24"},{"key":"e_1_2_1_42_1","unstructured":"Shakti N. Wadekar Abhishek Chaurasia Aman Chadha and Eugenio Culurciello. 2024. The Evolution of Multimodal Model Architectures. arxiv:2405.17927. arxiv:2405.17927"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/MedAI59581.2023.00044"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640406"},{"key":"e_1_2_1_45_1","unstructured":"Irene Weber. 2024. Large Language Models as Software Components: A Taxonomy for LLM-Integrated Applications. arxiv:2406.10300. arxiv:2406.10300"},{"key":"e_1_2_1_46_1","volume-title":"Willard and R\u00e9mi Louf","author":"Brandon","year":"2023","unstructured":"Brandon T. Willard and R\u00e9mi Louf. 2023. Efficient Guided Generation for Large Language Models. arxiv:2307.09702. arxiv:2307.09702"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3617232.3624858"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3617232.3624847"},{"key":"e_1_2_1_49_1","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang Guanting Dong Haoran Wei Huan Lin Jialong Tang Jialin Wang Jian Yang Jianhong Tu Jianwei Zhang Jianxin Ma Jianxin Yang Jin Xu Jingren Zhou Jinze Bai Jinzheng He Junyang Lin Kai Dang Keming Lu Keqin Chen Kexin Yang Mei Li Mingfeng Xue Na Ni Pei Zhang Peng Wang Ru Peng Rui Men Ruize Gao Runji Lin Shijie Wang Shuai Bai Sinan Tan Tianhang Zhu Tianhao Li Tianyu Liu Wenbin Ge Xiaodong Deng Xiaohuan Zhou Xingzhang Ren Xinyu Zhang Xipin Wei Xuancheng Ren Xuejing Liu Yang Fan Yang Yao Yichang Zhang Yu Wan Yunfei Chu Yuqiong Liu Zeyu Cui Zhenru Zhang Zhifang Guo and Zhihao Fan. 2024. Qwen2 Technical Report. arxiv:2407.10671. arxiv:2407.10671"},{"key":"e_1_2_1_50_1","volume-title":"Orca: A Distributed Serving System for Transformer-Based Generative Models. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)","author":"Yu Gyeong-In","year":"2022","unstructured":"Gyeong-In Yu, Joo Seong Jeong, Geon-Woo Kim, Soojeong Kim, and Byung-Gon Chun. 2022. Orca: A Distributed Serving System for Transformer-Based Generative Models. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22). USENIX Association, Carlsbad, CA. 521\u2013538. isbn:978-1-939133-28-1 https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/yu"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.14778\/3514061.3514069"},{"key":"e_1_2_1_52_1","volume-title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. Article","author":"Zheng Lianmin","year":"2020","unstructured":"Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. 2023. Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. Article 2020, 29 pages."},{"key":"e_1_2_1_53_1","volume-title":"Ansor: Generating High-Performance Tensor Programs for Deep Learning. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20)","author":"Zheng Lianmin","year":"2020","unstructured":"Lianmin Zheng, Chengfan Jia, Minmin Sun, Zhao Wu, Cody Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, Joseph E. Gonzalez, and Ion Stoica. 2020. Ansor: Generating High-Performance Tensor Programs for Deep Learning. In 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20). USENIX Association, 863\u2013879. isbn:978-1-939133-19-9 https:\/\/www.usenix.org\/conference\/osdi20\/presentation\/zheng"},{"key":"e_1_2_1_54_1","volume-title":"Shiyi Cao, Christos Kozyrakis, Ion Stoica, Joseph E. Gonzalez, Clark Barrett, and Ying Sheng.","author":"Zheng Lianmin","year":"2025","unstructured":"Lianmin Zheng, Liangsheng Yin, Zhiqiang Xie, Chuyue Sun, Jeff Huang, Cody Hao Yu, Shiyi Cao, Christos Kozyrakis, Ion Stoica, Joseph E. Gonzalez, Clark Barrett, and Ying Sheng. 2025. SGLang: Efficient Execution of Structured Language Model Programs. Article 2000, 27 pages. isbn:9798331314385"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651336"}],"container-title":["Proceedings of the ACM on Programming Languages"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3763092","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:41:09Z","timestamp":1760031669000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3763092"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,9]]},"references-count":55,"journal-issue":{"issue":"OOPSLA2","published-print":{"date-parts":[[2025,10,9]]}},"alternative-id":["10.1145\/3763092"],"URL":"https:\/\/doi.org\/10.1145\/3763092","relation":{},"ISSN":["2475-1421"],"issn-type":[{"value":"2475-1421","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,9]]},"assertion":[{"value":"2025-03-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-12","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}