{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T07:17:21Z","timestamp":1783408641113,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":21,"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"}],"funder":[{"name":"National Natural Science Foundarion of China","award":["W2542035"],"award-info":[{"award-number":["W2542035"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,12]]},"DOI":"10.1145\/3786181.3788729","type":"proceedings-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T06:28:24Z","timestamp":1783405704000},"page":"67-72","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Statistical Independence Aware Caching for LLM Workflows"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0259-6174","authenticated-orcid":false,"given":"Yihan","family":"Dai","sequence":"first","affiliation":[{"name":"Key Laboratory of HCST (PKU), MoE, SCS, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3171-5194","authenticated-orcid":false,"given":"Dimitrios Stamatios","family":"Bouras","sequence":"additional","affiliation":[{"name":"Key Laboratory of HCST (PKU), MoE, SCS, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6027-231X","authenticated-orcid":false,"given":"Haoxiang","family":"Jia","sequence":"additional","affiliation":[{"name":"Key Laboratory of HCST (PKU), MoE, SCS, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6088-4993","authenticated-orcid":false,"given":"Sergey","family":"Mechatev","sequence":"additional","affiliation":[{"name":"Key Laboratory of HCST (PKU), MoE, SCS, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,6]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"2025. FloTorch: Agent-Aware Caching and Modular AI Pipelines. https:\/\/flotorch.ai. Accessed: 2025-10-13."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.nlposs-1.24"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","unstructured":"Lo\u00efc Besnard Pedro Pinto Imane Lasri Jo\u00e3o Bispo Erven Rohou and Jo\u00e3o\u00a0M.P. Cardoso. 2019. A framework for automatic and parameterizable memoization. SoftwareX 10 (2019) 100322. 10.1016\/j.softx.2019.100322","DOI":"10.1016\/j.softx.2019.100322"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/1882486.1882491"},{"key":"e_1_3_3_2_6_2","unstructured":"Harrison Chase. 2023. LangChain: Building applications with large language models through composability. https:\/\/python.langchain.com. Accessed: 2025-10-13."},{"key":"e_1_3_3_2_7_2","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique\u00a0Ponde de Oliveira\u00a0Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman Alex Ray Raul Puri Gretchen Krueger Michael Petrov Heidy Khlaaf Girish Sastry Pamela Mishkin Brooke Chan Scott Gray Nick Ryder Mikhail Pavlov Alethea Power Lukasz Kaiser Mohammad Bavarian Clemens Winter Philippe Tillet Felipe\u00a0Petroski Such Dave Cummings Matthias Plappert Fotios Chantzis Elizabeth Barnes Ariel Herbert-Voss William\u00a0Hebgen Guss Alex Nichol Alex Paino Nikolas Tezak Jie Tang Igor Babuschkin Suchir Balaji Shantanu Jain William Saunders Christopher Hesse Andrew\u00a0N. Carr Jan Leike Josh Achiam Vedant Misra Evan Morikawa Alec Radford Matthew Knight Miles Brundage Mira Murati Katie Mayer Peter Welinder Bob McGrew Dario Amodei Sam McCandlish Ilya Sutskever and Wojciech Zaremba. 2021. Evaluating Large Language Models Trained on Code. arxiv:https:\/\/arXiv.org\/abs\/2107.03374\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2107.03374"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Andy Cockburn Pierre Dragicevic Lonni Besan\u00e7on and Carl Gutwin. 2020. Threats of a replication crisis in empirical computer science. Commun. ACM 63 8 (2020) 70\u201379.","DOI":"10.1145\/3360311"},{"key":"e_1_3_3_2_9_2","volume-title":"Design patterns: elements of reusable object-oriented software","author":"Gamma Erich","year":"1995","unstructured":"Erich Gamma, Richard Helm, Ralph Johnson, and John Vlissides. 1995. Design patterns: elements of reusable object-oriented software. Pearson Deutschland GmbH."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Charles Garrod Amit Manjhi Anastasia Ailamaki Bruce Maggs Todd Mowry Christopher Olston and Anthony Tomasic. 2008. Scalable query result caching for web applications. Proc. VLDB Endow. 1 1 (Aug. 2008) 550\u2013561. 10.14778\/1453856.1453917","DOI":"10.14778\/1453856.1453917"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ipdps64566.2025.00117"},{"key":"e_1_3_3_2_12_2","unstructured":"Christian Hobelsberger Theresa Winner Andreas Nawroth Oliver Mitevski and Anna-Carolina Haensch. 2025. Systematic Evaluation of Uncertainty Estimation Methods in Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2510.20460\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2510.20460"},{"key":"e_1_3_3_2_13_2","unstructured":"Haoxiang Jia Robbie Morris He Ye Federica Sarro and Sergey Mechtaev. 2025. Automated Repair of Ambiguous Problem Descriptions for LLM-Based Code Generation. arxiv:https:\/\/arXiv.org\/abs\/2505.07270\u00a0[cs.SE] https:\/\/arxiv.org\/abs\/2505.07270"},{"key":"e_1_3_3_2_14_2","unstructured":"Lorenz Kuhn Yarin Gal and Sebastian Farquhar. 2023. Semantic uncertainty: Linguistic invariances for uncertainty estimation in natural language generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.09664 (2023)."},{"key":"e_1_3_3_2_15_2","unstructured":"Woosuk Kwon Zhuohan Li Siyuan Zhuang Ying Sheng Lianmin Zheng Cody\u00a0Hao Yu Joseph\u00a0E. Gonzalez Hao Zhang and Ion Stoica. 2023. Efficient Memory Management for Large Language Model Serving with PagedAttention. arxiv:https:\/\/arXiv.org\/abs\/2309.06180\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2309.06180"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i18.34120"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Aman Madaan Niket Tandon Prakhar Gupta Skyler Hallinan Luyu Gao Sarah Wiegreffe Uri Alon Nouha Dziri Shrimai Prabhumoye Yiming Yang Shashank Gupta Bodhisattwa\u00a0Prasad Majumder Katherine Hermann Sean Welleck Amir Yazdanbakhsh and Peter Clark. 2023. Self-Refine: Iterative Refinement with Self-Feedback. arxiv:https:\/\/arXiv.org\/abs\/2303.17651\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2303.17651","DOI":"10.52202\/075280-2019"},{"key":"e_1_3_3_2_18_2","unstructured":"Potsawee Manakul Adian Liusie and Mark J.\u00a0F. Gales. 2023. SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2303.08896\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2303.08896"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.1402"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/2804302.2804317"},{"key":"e_1_3_3_2_21_2","unstructured":"Noah Shinn Federico Cassano Edward Berman Ashwin Gopinath Karthik Narasimhan and Shunyu Yao. 2023. Reflexion: Language Agents with Verbal Reinforcement Learning. arxiv:https:\/\/arXiv.org\/abs\/2303.11366\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2303.11366"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3759425.3763396"}],"event":{"name":"LLM4Code '26: 3rd International Workshop on Large Language Models For Code","location":"Rio de Janeiro Brazil","acronym":"LLM4Code '26","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the 3rd International Workshop on Large Language Models For Code"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3786181.3788729","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T06:36:58Z","timestamp":1783406218000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786181.3788729"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":21,"alternative-id":["10.1145\/3786181.3788729","10.1145\/3786181"],"URL":"https:\/\/doi.org\/10.1145\/3786181.3788729","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-07-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}