{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T01:07:41Z","timestamp":1755220061455,"version":"3.43.0"},"reference-count":25,"publisher":"Association for Computing Machinery (ACM)","issue":"1","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGOPS Oper. Syst. Rev."],"published-print":{"date-parts":[[2025,8,4]]},"abstract":"<jats:p>Conventional Application Programming Interfaces (APIs) are designed for human developers. However, when Large Language Models (LLMs) act as API clients, these humancentric design choices may fail to harness the potential of LLMs, thus causing excessive overhead and task failures. We present Symphony AP1s, a class of semi-open APIs allowing LLMs to extend the API's internal logic at runtime, under the constraints of safety and controllability. Our case studies using the POSIX 'find' utility and the Robot 'PickAndPlace' API show that Symphony APIs can enable LLMs to extend API capabilities in a cost-effective and controllable manner.<\/jats:p>","DOI":"10.1145\/3759441.3759445","type":"journal-article","created":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T14:43:44Z","timestamp":1754491424000},"page":"17-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Large Language Model-Friendly APls"],"prefix":"10.1145","volume":"59","author":[{"given":"Yuan","family":"Wang","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences"}]},{"given":"Zhenyuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Nanjing University"}]},{"given":"Zhanbo","family":"Wang","sequence":"additional","affiliation":[{"name":"Xi' an Jiaotong University"}]},{"given":"Mingyu","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of System Software, Institute of Software, Chinese Academy of Sciences"}]},{"given":"Zhilin","family":"Wu","sequence":"additional","affiliation":[{"name":"Key Laboratory of System Software, Institute of Software, Chinese Academy of Sciences"}]},{"given":"Haibo","family":"Chen","sequence":"additional","affiliation":[{"name":"Key Laboratory of System Software, Institute of Software, Chinese Academy of Sciences"}]}],"member":"320","published-online":{"date-parts":[[2025,8,6]]},"reference":[{"volume-title":"Model context protocol (mcp) specification. https:\/\/www.claudemcp.com\/zh","year":"2024","key":"e_1_2_1_1_1","unstructured":"Anthropic. Model context protocol (mcp) specification. https:\/\/www.claudemcp.com\/zh, 2024. Accessed: 2025-04-13."},{"key":"e_1_2_1_2_1","volume-title":"Language models are few-shot learners. Advances in neural information processing systems, 33:1877-1901","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. Language models are few-shot learners. Advances in neural information processing systems, 33:1877-1901, 2020."},{"key":"e_1_2_1_3_1","volume-title":"Coder: Issue resolving with multiagent and task graphs. ArXiv, abs\/2406.01304","author":"Chen Dong","year":"2024","unstructured":"Dong Chen, Shaoxin Lin, Muhan Zeng, Daoguang Zan, Jian-Gang Wang, Anton Cheshkov, Jun Sun, Hao Yu, Guoliang Dong, Artem Aliev, Jie Wang, Xiao Cheng, Guangtai Liang, Yuchi Ma, Pan Bian, Tao Xie, and Qianxiang Wang. Coder: Issue resolving with multiagent and task graphs. ArXiv, abs\/2406.01304, 2024."},{"key":"e_1_2_1_4_1","volume-title":"What's wrong with your code generated by large language models? an extensive study. arXiv preprint arXiv:2407.06153","author":"Dou Shihan","year":"2024","unstructured":"Shihan Dou, Haoxiang Jia, Shenxi Wu, Huiyuan Zheng, Weikang Zhou, Muling Wu, Mingxu Chai, Jessica Fan, Caishuang Huang, Yunbo Tao, et al. What's wrong with your code generated by large language models? an extensive study. arXiv preprint arXiv:2407.06153, 2024."},{"key":"e_1_2_1_5_1","volume-title":"Dynamically program the kernel for efficient networking, observability, tracing, and security","author":"BPF","year":"2024","unstructured":"eBPF community. Dynamically program the kernel for efficient networking, observability, tracing, and security, 2024. https:\/\/ebpf.io\/."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"e_1_2_1_7_1","unstructured":"The IEEE and The Open Group. Posix.1- 2024 2024. https:\/\/pubs.opengroup.org\/ onlinepubs\/9799919799\/."},{"key":"e_1_2_1_8_1","volume-title":"Shell command language","author":"The IEEE and The Open Group","year":"2024","unstructured":"The IEEE and The Open Group. Shell command language, 2024. https:\/\/pubs.opengroup.org\/ onlinepubs\/9699919799\/utilities\/V3_chap02. html."},{"key":"e_1_2_1_9_1","unstructured":"The IEEE and The Open Group. Utilities 2024. https:\/\/pubs.opengroup.org\/onlinepubs\/ 9699919799\/idx\/utilities.html."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510203"},{"key":"e_1_2_1_11_1","volume-title":"Andrea Madotto, and Pascale Fung. Survey of hallucination in natural language generation. ACM Comput. Surv., 55(12)","author":"Ji Ziwei","year":"2023","unstructured":"Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. Survey of hallucination in natural language generation. ACM Comput. Surv., 55(12), March 2023."},{"key":"e_1_2_1_12_1","volume-title":"Challenges and applications of large language models","author":"Kaddour Jean","year":"2023","unstructured":"Jean Kaddour, Joshua Harris, Maximilian Mozes, Herbie Bradley, Roberta Raileanu, and Robert McHardy. Challenges and applications of large language models, 2023."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-024-00550-5"},{"key":"e_1_2_1_14_1","volume-title":"October","author":"Lamothe Maxime","year":"2021","unstructured":"Maxime Lamothe, Yann-Ga\u00ebl Gu\u00e9h\u00e9neuc, and Weiyi Shang. A systematic review of api evolution literature. ACM Comput. Surv., 54(8), October 2021."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.187"},{"key":"e_1_2_1_16_1","volume-title":"Personal llm agents: Insights and survey about the capability, efficiency and security","author":"Li Yuanchun","year":"2024","unstructured":"Yuanchun Li, Hao Wen, Weijun Wang, Xiangyu Li, Yizhen Yuan, Guohong Liu, Jiacheng Liu, Wenxing Xu, Xiang Wang, Yi Sun, Rui Kong, Yile Wang, Hanfei Geng, Jian Luan, Xuefeng Jin, Zilong Ye, Guanjing Xiong, Fan Zhang, Xiang Li, Mengwei Xu, Zhijun Li, Peng Li, Yang Liu, Ya-Qin Zhang, and Yunxin Liu. Personal llm agents: Insights and survey about the capability, efficiency and security, 2024."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00109"},{"key":"e_1_2_1_19_1","volume-title":"Function calling in openai api. https:\/\/platform.openai.com\/docs\/guides\/ function-calling","author":"AI.","year":"2023","unstructured":"OpenAI. Function calling in openai api. https:\/\/platform.openai.com\/docs\/guides\/ function-calling, 2023. Accessed: 2025-04-13."},{"key":"e_1_2_1_20_1","volume-title":"Less is more: Optimizing function calling for llm execution on edge devices","author":"Paramanayakam Varatheepan","year":"2024","unstructured":"Varatheepan Paramanayakam, Andreas Karatzas, Iraklis Anagnostopoulos, and Dimitrios Stamoulis. Less is more: Optimizing function calling for llm execution on edge devices, 2024."},{"key":"e_1_2_1_21_1","unstructured":"Shishir G. Patil Tianjun Zhang Vivian Fang Noppapon C Roy Huang Aaron Hao Martin Casado Joseph E. Gonzalez Raluca Ada Popa Ion Stoica Uc Berkeley and Andreessen Horowitz. Goex: Perspectives and designs towards a runtime for autonomous llm applications. ArXiv abs\/2404.06921 2024."},{"key":"e_1_2_1_22_1","volume-title":"Gorilla: Large language model connected with massive apis. ArXiv, abs\/2305.15334","author":"Patil Shishir G.","year":"2023","unstructured":"Shishir G. Patil, Tianjun Zhang, Xin Wang, and Joseph E. Gonzalez. Gorilla: Large language model connected with massive apis. ArXiv, abs\/2305.15334, 2023."},{"key":"e_1_2_1_23_1","volume-title":"The Twelfth International Conference on Learning Representations","author":"Qin Yujia","year":"2024","unstructured":"Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, Sihan Zhao, Lauren Hong, Runchu Tian, Ruobing Xie, Jie Zhou, Mark Gerstein, dahai li, Zhiyuan Liu, and Maosong Sun. ToolLLM: Facilitating large language models to master 16000+ real-world APIs. In The Twelfth International Conference on Learning Representations, 2024."},{"key":"e_1_2_1_24_1","volume-title":"Where do large language models fail when generating code? arXiv preprint arXiv:2406.08731","author":"Wang Zhijie","year":"2024","unstructured":"Zhijie Wang, Zijie Zhou, Da Song, Yuheng Huang, Shengmai Chen, Lei Ma, and Tianyi Zhang. Where do large language models fail when generating code? arXiv preprint arXiv:2406.08731, 2024."},{"key":"e_1_2_1_25_1","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Yang John","year":"2024","unstructured":"John Yang, Carlos E Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik R Narasimhan, and Ofir Press. SWE-agent: Agent-computer interfaces enable automated software engineering. In The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024."}],"container-title":["ACM SIGOPS Operating Systems Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3759441.3759445","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T19:50:28Z","timestamp":1754596228000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3759441.3759445"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,4]]},"references-count":25,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,8,4]]}},"alternative-id":["10.1145\/3759441.3759445"],"URL":"https:\/\/doi.org\/10.1145\/3759441.3759445","relation":{},"ISSN":["0163-5980"],"issn-type":[{"type":"print","value":"0163-5980"}],"subject":[],"published":{"date-parts":[[2025,8,4]]},"assertion":[{"value":"2025-08-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}