{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T13:02:56Z","timestamp":1780664576468,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":72,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T00:00:00Z","timestamp":1777161600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,27]]},"DOI":"10.1145\/3767295.3803622","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T20:20:04Z","timestamp":1777062004000},"page":"1862-1878","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AIMS: Cost-Efficient LLM-Based Agent Deployment in Hybrid Cloud-Edge Environments"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7611-319X","authenticated-orcid":false,"given":"Shiyi","family":"Liu","sequence":"first","affiliation":[{"name":"University of Virginia, Charlottesville, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7548-6223","authenticated-orcid":false,"given":"Haiying","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Virginia, Charlottesville, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3192-3057","authenticated-orcid":false,"given":"Shuai","family":"Che","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7600-0488","authenticated-orcid":false,"given":"Mahdi","family":"Ghandi","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8103-3581","authenticated-orcid":false,"given":"Mingqin","family":"Li","sequence":"additional","affiliation":[{"name":"Shopify, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,26]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Chemcrow: Augmenting large-language models with chemistry tools. arXiv preprint arXiv:2304.05376","author":"Bran Andres M","year":"2023","unstructured":"Andres M Bran, Sam Cox, Andrew D White, and Philippe Schwaller. Chemcrow: Augmenting large-language models with chemistry tools. arXiv preprint arXiv:2304.05376, 2023."},{"key":"e_1_3_2_1_2_1","volume-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","author":"Brown Tom B.","year":"2020","unstructured":"Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. Language models are few-shot learners. In Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, and Hsuan-Tien Lin, editors, Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6\u201312, 2020, virtual, 2020."},{"key":"e_1_3_2_1_3_1","volume-title":"Frugalgpt: How to use large language models while reducing cost and improving performance. arXiv preprint arXiv:2305.05176","author":"Chen Lingjiao","year":"2023","unstructured":"Lingjiao Chen, Matei Zaharia, and James Zou. Frugalgpt: How to use large language models while reducing cost and improving performance. arXiv preprint arXiv:2305.05176, 2023."},{"key":"e_1_3_2_1_4_1","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Pond\u00e9 de Oliveira Pinto 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 Petroski Such Dave Cummings Matthias Plappert Fotios Chantzis Elizabeth Barnes Ariel Herbert-Voss William Hebgen Guss Alex Nichol Alex Paino Nikolas Tezak Jie Tang Igor Babuschkin Suchir Balaji Shantanu Jain William Saunders Christopher Hesse Andrew N. Carr Jan Leike Joshua 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. Evaluating large language models trained on code. CoRR abs\/2107.03374 2021."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629553"},{"key":"e_1_3_2_1_6_1","volume-title":"Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168","author":"Cobbe Karl","year":"2021","unstructured":"Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, et al. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168, 2021."},{"key":"e_1_3_2_1_7_1","volume-title":"On efficient approximate queries over machine learning models. arXiv preprint arXiv:2206.02845","author":"Ding Dujian","year":"2022","unstructured":"Dujian Ding, Sihem Amer-Yahia, and Laks VS Lakshmanan. On efficient approximate queries over machine learning models. arXiv preprint arXiv:2206.02845, 2022."},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Learning Representations","author":"Ding Dujian","year":"2023","unstructured":"Dujian Ding, Ankur Mallick, Chi Wang, Robert Sim, Subhabrata Mukherjee, Victor R\u00fchle, Laks VS Lakshmanan, and Ahmed Hassan Awadallah. Hybrid llm: Cost-efficient and quality-aware query routing. In International Conference on Learning Representations, 2023."},{"key":"e_1_3_2_1_9_1","volume-title":"Drop: A reading comprehension benchmark requiring discrete reasoning over paragraphs. arXiv preprint arXiv:1903.00161","author":"Dua Dheeru","year":"2019","unstructured":"Dheeru Dua, Yizhong Wang, Pradeep Dasigi, Gabriel Stanovsky, Sameer Singh, and Matt Gardner. Drop: A reading comprehension benchmark requiring discrete reasoning over paragraphs. arXiv preprint arXiv:1903.00161, 2019."},{"key":"e_1_3_2_1_10_1","volume-title":"Chatgpt enterprise: The future of ai in business. https:\/\/explodingtopics.com\/blog\/chatgpt-enterprise","author":"Topics Exploding","year":"2025","unstructured":"Exploding Topics. Chatgpt enterprise: The future of ai in business. https:\/\/explodingtopics.com\/blog\/chatgpt-enterprise, 2025. Accessed: Mar. 6, 2026."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3717481"},{"key":"e_1_3_2_1_12_1","first-page":"10430","volume-title":"International Conference on Machine Learning","author":"Fu Yao","unstructured":"Yao Fu, Hao Peng, Litu Ou, Ashish Sabharwal, and Tushar Khot. Specializing smaller language models towards multi-step reasoning. In International Conference on Machine Learning, pages 10421\u201310430. PMLR, 2023."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696072"},{"key":"e_1_3_2_1_14_1","volume-title":"Balancing autonomy and alignment: A multidimensional taxonomy for autonomous llm-powered multi-agent architectures. arXiv preprint arXiv:2310.03659","author":"H\u00e4ndler Thorsten","year":"2023","unstructured":"Thorsten H\u00e4ndler. Balancing autonomy and alignment: A multidimensional taxonomy for autonomous llm-powered multi-agent architectures. arXiv preprint arXiv:2310.03659, 2023."},{"key":"e_1_3_2_1_15_1","volume-title":"Measuring mathematical problem solving with the MATH dataset. CoRR, abs\/2103.03874","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. Measuring mathematical problem solving with the MATH dataset. CoRR, abs\/2103.03874, 2021."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651380"},{"key":"e_1_3_2_1_17_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685, 2021."},{"key":"e_1_3_2_1_18_1","volume-title":"Automated design of agentic systems. arXiv preprint arXiv:2408.08435","author":"Hu Shengran","year":"2024","unstructured":"Shengran Hu, Cong Lu, and Jeff Clune. Automated design of agentic systems. arXiv preprint arXiv:2408.08435, 2024."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.792"},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Learning Representations","author":"Kag Anil","year":"2023","unstructured":"Anil Kag and Igor Fedorov. Efficient edge inference by selective query. In International Conference on Learning Representations, 2023."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_22_1","volume-title":"Langgraph: A low-level orchestration framework for building stateful agents. https:\/\/github.com\/langchain-ai\/langgraph","author":"LangChain","year":"2024","unstructured":"LangChain AI. Langgraph: A low-level orchestration framework for building stateful agents. https:\/\/github.com\/langchain-ai\/langgraph, 2024. Accessed: Mar. 6, 2026."},{"key":"e_1_3_2_1_23_1","first-page":"5333","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023","author":"Li Yifei","year":"2023","unstructured":"Yifei Li, Zeqi Lin, Shizhuo Zhang, Qiang Fu, Bei Chen, Jian-Guang Lou, and Weizhu Chen. Making language models better reasoners with step-aware verifier. In Anna Rogers, Jordan L. Boyd-Graber, and Naoaki Okazaki, editors, Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9\u201314, 2023, pages 5315\u20135333. Association for Computational Linguistics, 2023."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.34133\/icomputing.0063"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems, NIPS '23","author":"Lu Pan","year":"2023","unstructured":"Pan Lu, Baolin Peng, Hao Cheng, Michel Galley, Kai-Wei Chang, Ying Nian Wu, Song-Chun Zhu, and Jianfeng Gao. Chameleon: plug-and-play compositional reasoning with large language models. In Proceedings of the 37th International Conference on Neural Information Processing Systems, NIPS '23, Red Hook, NY, USA, 2023. Curran Associates Inc."},{"key":"e_1_3_2_1_26_1","volume-title":"Augmented language models: a survey. arXiv preprint arXiv:2302.07842","author":"Mialon Gr\u00e9goire","year":"2023","unstructured":"Gr\u00e9goire Mialon, Roberto Dess\u00ec, Maria Lomeli, Christoforos Nalmpantis, Ram Pasunuru, Roberta Raileanu, Baptiste Rozi\u00e8re, Timo Schick, Jane Dwivedi-Yu, Asli Celikyilmaz, et al. Augmented language models: a survey. arXiv preprint arXiv:2302.07842, 2023."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651335"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640411"},{"key":"e_1_3_2_1_29_1","volume-title":"Semantic Kernel: An open-source SDK for integrating LLMs into applications. https:\/\/github.com\/microsoft\/semantic-kernel","year":"2023","unstructured":"Microsoft. Semantic Kernel: An open-source SDK for integrating LLMs into applications. https:\/\/github.com\/microsoft\/semantic-kernel, 2023. Accessed: 2025."},{"key":"e_1_3_2_1_30_1","volume-title":"et al. Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332","author":"Nakano Reiichiro","year":"2021","unstructured":"Reiichiro Nakano, Jacob Hilton, Suchir Balaji, Jeff Wu, Long Ouyang, Christina Kim, Christopher Hesse, Shantanu Jain, Vineet Kosaraju, William Saunders, et al. Webgpt: Browser-assisted question-answering with human feedback. arXiv preprint arXiv:2112.09332, 2021."},{"key":"e_1_3_2_1_31_1","volume-title":"Minions: Cost-efficient collaboration between on-device and cloud language models. arXiv preprint arXiv:2502.15964","author":"Narayan Avanika","year":"2025","unstructured":"Avanika Narayan, Dan Biderman, Sabri Eyuboglu, Avner May, Scott Linderman, James Zou, and Christopher Re. Minions: Cost-efficient collaboration between on-device and cloud language models. arXiv preprint arXiv:2502.15964, 2025."},{"key":"e_1_3_2_1_32_1","volume-title":"How much does it cost to use gpt models? gpt-3 pricing explained. https:\/\/neoteric.eu\/blog\/how-much-does-it-cost-to-use-gpt-models-gpt-3-pricing-explained\/","year":"2023","unstructured":"Neoteric. How much does it cost to use gpt models? gpt-3 pricing explained. https:\/\/neoteric.eu\/blog\/how-much-does-it-cost-to-use-gpt-models-gpt-3-pricing-explained\/, 2023. Accessed: Mar. 6, 2026."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640383"},{"key":"e_1_3_2_1_34_1","volume-title":"Routellm: Learning to route llms with preference data. arXiv preprint arXiv:2406.18665","author":"Ong Isaac","year":"2024","unstructured":"Isaac Ong, Amjad Almahairi, Vincent Wu, Wei-Lin Chiang, Tianhao Wu, Joseph E Gonzalez, M Waleed Kadous, and Ion Stoica. Routellm: Learning to route llms with preference data. arXiv preprint arXiv:2406.18665, 2024."},{"key":"e_1_3_2_1_35_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35:27730\u201327744, 2022.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.259"},{"key":"e_1_3_2_1_37_1","first-page":"15186","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Qian Chen","year":"2024","unstructured":"Chen Qian, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong, Juyuan Xu, Dahai Li, Zhiyuan Liu, and Maosong Sun. ChatDev: Communicative agents for software development. In Lun-Wei Ku, Andre Martins, and Vivek Srikumar, editors, Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15174\u201315186, Bangkok, Thailand, August 2024. Association for Computational Linguistics."},{"key":"e_1_3_2_1_38_1","volume-title":"Benchmarking agentic workflow generation. arXiv preprint arXiv:2410.07869","author":"Qiao Shuofei","year":"2024","unstructured":"Shuofei Qiao, Runnan Fang, Zhisong Qiu, Xiaobin Wang, Ningyu Zhang, Yong Jiang, Pengjun Xie, Fei Huang, and Huajun Chen. Benchmarking agentic workflow generation. arXiv preprint arXiv:2410.07869, 2024."},{"key":"e_1_3_2_1_39_1","volume-title":"et al. Toolllm: Facilitating large language models to master 16000+ real-world apis. arXiv preprint arXiv:2307.16789","author":"Qin Yujia","year":"2023","unstructured":"Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, et al. Toolllm: Facilitating large language models to master 16000+ real-world apis. arXiv preprint arXiv:2307.16789, 2023."},{"key":"e_1_3_2_1_40_1","first-page":"1827","volume-title":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2024 -","volume":"22","author":"Ranaldi Leonardo","year":"2024","unstructured":"Leonardo Ranaldi and Andr\u00e9 Freitas. Aligning large and small language models via chain-of-thought reasoning. In Yvette Graham and Matthew Purver, editors, Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2024 - Volume 1: Long Papers, St. Julian's, Malta, March 17\u201322, 2024, pages 1812\u20131827. Association for Computational Linguistics, 2024."},{"key":"e_1_3_2_1_41_1","first-page":"3992","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLPIJCNLP)","author":"Reimers Nils","year":"2019","unstructured":"Nils Reimers and Iryna Gurevych. Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In Kentaro Inui, Jing Jiang, Vincent Ng, and Xiaojun Wan, editors, Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLPIJCNLP), pages 3982\u20133992, Hong Kong, China, November 2019. Association for Computational Linguistics."},{"key":"e_1_3_2_1_42_1","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Schick Timo","year":"2023","unstructured":"Timo Schick, Jane Dwivedi-Yu, Roberto Dess\u00ec, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. Toolformer: Language models can teach themselves to use tools. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, 2023."},{"key":"e_1_3_2_1_43_1","volume-title":"The inference cost of search disruption - large language model cost analysis. https:\/\/semianalysis.com\/2023\/02\/09\/the-inference-cost-of-search-disruption\/","year":"2023","unstructured":"SemiAnalysis. The inference cost of search disruption - large language model cost analysis. https:\/\/semianalysis.com\/2023\/02\/09\/the-inference-cost-of-search-disruption\/, 2023. Accessed: Mar. 6, 2026."},{"key":"e_1_3_2_1_44_1","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Shen Yongliang","year":"2023","unstructured":"Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, and Yueting Zhuang. Hugginggpt: Solving AI tasks with chatgpt and its friends in hugging face. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, 2023."},{"key":"e_1_3_2_1_45_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Shinn Noah","year":"2023","unstructured":"Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik R Narasimhan, and Shunyu Yao. Reflexion: Language agents with verbal reinforcement learning. In Thirty-seventh Conference on Neural Information Processing Systems, 2023."},{"key":"e_1_3_2_1_46_1","volume-title":"https:\/\/github.com\/Significant-Gravitas\/AutoGPT","author":"Gravitas Significant","year":"2023","unstructured":"Significant Gravitas. Autogpt. https:\/\/github.com\/Significant-Gravitas\/AutoGPT, 2023. Accessed: Mar. 6, 2026."},{"key":"e_1_3_2_1_47_1","volume-title":"Transactions on Machine Learning Research","author":"Sumers Theodore","year":"2024","unstructured":"Theodore Sumers, Shunyu Yao, Karthik Narasimhan, and Thomas Griffiths. Cognitive architectures for language agents. Transactions on Machine Learning Research, 2024. Survey Certification."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651359"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3717469"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990517"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000013087.49260.fb"},{"key":"e_1_3_2_1_52_1","volume-title":"Transactions on Machine Learning Research","author":"Wang Guanzhi","year":"2024","unstructured":"Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. Voyager: An open-ended embodied agent with large language models. Transactions on Machine Learning Research, 2024."},{"key":"e_1_3_2_1_53_1","volume-title":"ICML 2024 Workshop on Foundation Models in the Wild","author":"Wang Kuan","year":"2024","unstructured":"Kuan Wang, Yadong Lu, Michael Santacroce, Yeyun Gong, Chao Zhang, et al. Adapting llm agents with universal feedback in communication. In ICML 2024 Workshop on Foundation Models in the Wild, 2024."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40231-1"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.127"},{"key":"e_1_3_2_1_56_1","volume-title":"International Conference on Learning Representations","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Maarten Bosma, Vincent Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai, and Quoc V Le. Finetuned language models are zero-shot learners. In International Conference on Learning Representations, 2022."},{"key":"e_1_3_2_1_57_1","volume-title":"Transactions on Machine Learning Research","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, Ed H. Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus. Emergent abilities of large language models. Transactions on Machine Learning Research, 2022. Survey Certification."},{"key":"e_1_3_2_1_58_1","volume-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. Chain-of-thought prompting elicits reasoning in large language models. In Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh, editors, Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, 2022."},{"key":"e_1_3_2_1_59_1","volume-title":"COLM 2024","author":"Wu Qingyun","year":"2024","unstructured":"Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang (Eric) Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Ahmed Awadallah, Ryen W. White, Doug Burger, and Chi Wang. Autogen: Enabling next-gen llm applications via multi-agent conversation. In COLM 2024, August 2024."},{"key":"e_1_3_2_1_60_1","volume-title":"Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems","author":"Wu Wenshan","year":"2024","unstructured":"Wenshan Wu, Shaoguang Mao, Yadong Zhang, Yan Xia, Li Dong, Lei Cui, and Furu Wei. Mind's eye of llms: Visualization-of-thought elicits spatial reasoning in large language models. In Amir Globersons, Lester Mackey, Danielle Belgrave, Angela Fan, Ulrich Paquet, Jakub M. Tomczak, and Cheng Zhang, editors, Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024, 2024."},{"key":"e_1_3_2_1_61_1","volume-title":"The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864","author":"Xi Zhiheng","year":"2023","unstructured":"Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, et al. The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864, 2023."},{"key":"e_1_3_2_1_62_1","volume-title":"Rewoo: Decoupling reasoning from observations for efficient augmented language models. arXiv preprint arXiv:2305.18323","author":"Xu Binfeng","year":"2023","unstructured":"Binfeng Xu, Zhiyuan Peng, Bowen Lei, Subhabrata Mukherjee, Yuchen Liu, and Dongkuan Xu. Rewoo: Decoupling reasoning from observations for efficient augmented language models. arXiv preprint arXiv:2305.18323, 2023."},{"key":"e_1_3_2_1_63_1","first-page":"294","volume-title":"Findings of the Association for Computational Linguistics: ACL 2024","author":"Xu Canwen","year":"2024","unstructured":"Canwen Xu, Yichong Xu, Shuohang Wang, Yang Liu, Chenguang Zhu, and Julian McAuley. Small models are valuable plug-ins for large language models. In Lun-Wei Ku, Andre Martins, and Vivek Srikumar, editors, Findings of the Association for Computational Linguistics: ACL 2024, pages 283\u2013294, Bangkok, Thailand, August 2024. Association for Computational Linguistics."},{"key":"e_1_3_2_1_64_1","volume-title":"Qwen3 technical report. arXiv preprint arXiv:2505.09388","author":"Yang An","year":"2025","unstructured":"An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al. Qwen3 technical report. arXiv preprint arXiv:2505.09388, 2025."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1259"},{"key":"e_1_3_2_1_66_1","volume-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","author":"Yao Shunyu","year":"2022","unstructured":"Shunyu Yao, Howard Chen, John Yang, and Karthik Narasimhan. Webshop: Towards scalable real-world web interaction with grounded language agents. In Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh, editors, Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, 2022."},{"key":"e_1_3_2_1_67_1","volume-title":"React: Synergizing reasoning and acting in language models. CoRR, abs\/2210.03629","author":"Yao Shunyu","year":"2022","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. React: Synergizing reasoning and acting in language models. CoRR, abs\/2210.03629, 2022."},{"key":"e_1_3_2_1_68_1","first-page":"538","volume-title":"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. Orca: A distributed serving system for {Transformer-Based} generative models. In 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22), pages 521\u2013538, 2022."},{"key":"e_1_3_2_1_69_1","volume-title":"International Conference on Learning Representations","author":"Tianyi","year":"2020","unstructured":"Tianyi Zhang*, Varsha Kishore*, Felix Wu*, Kilian Q. Weinberger, and Yoav Artzi. Bertscore: Evaluating text generation with bert. In International Conference on Learning Representations, 2020."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.370"},{"key":"e_1_3_2_1_71_1","volume-title":"et al. Webarena: A realistic web environment for building autonomous agents. arXiv preprint arXiv:2307.13854","author":"Zhou Shuyan","year":"2023","unstructured":"Shuyan Zhou, Frank F Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, et al. Webarena: A realistic web environment for building autonomous agents. arXiv preprint arXiv:2307.13854, 2023."},{"key":"e_1_3_2_1_72_1","volume-title":"Ghost in the minecraft: Generally capable agents for open-world enviroments via large language models with text-based knowledge and memory. arXiv preprint arXiv:2305.17144","author":"Zhu Xizhou","year":"2023","unstructured":"Xizhou Zhu, Yuntao Chen, Hao Tian, Chenxin Tao, Weijie Su, Chenyu Yang, Gao Huang, Bin Li, Lewei Lu, Xiaogang Wang, et al. Ghost in the minecraft: Generally capable agents for open-world enviroments via large language models with text-based knowledge and memory. arXiv preprint arXiv:2305.17144, 2023."}],"event":{"name":"EUROSYS '26: 21st European Conference on Computer Systems","location":"McEwan Hall\/The University of Edinburgh Edinburgh Scotland UK","acronym":"EUROSYS '26","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 21st European Conference on Computer Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3767295.3803622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T12:08:00Z","timestamp":1780661280000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767295.3803622"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,26]]},"references-count":72,"alternative-id":["10.1145\/3767295.3803622","10.1145\/3767295"],"URL":"https:\/\/doi.org\/10.1145\/3767295.3803622","relation":{},"subject":[],"published":{"date-parts":[[2026,4,26]]},"assertion":[{"value":"2026-04-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}