{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T04:07:19Z","timestamp":1779422839946,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T00:00:00Z","timestamp":1779753600000},"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":[[2026,5,26]]},"DOI":"10.1145\/3786335.3813163","type":"proceedings-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T03:16:22Z","timestamp":1779419782000},"page":"1051-1069","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3462-3461","authenticated-orcid":false,"given":"Dzung","family":"Pham","sequence":"first","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2945-5434","authenticated-orcid":false,"given":"Kleomenis","family":"Katevas","sequence":"additional","affiliation":[{"name":"Brave Software, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1093-0125","authenticated-orcid":false,"given":"Ali","family":"Shahin Shamsabadi","sequence":"additional","affiliation":[{"name":"Brave Software, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5895-8903","authenticated-orcid":false,"given":"Hamed","family":"Haddadi","sequence":"additional","affiliation":[{"name":"Brave Software, London, United Kingdom and Imperial College London, London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,26]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Anthropic. 2026. Claude API Pricing. https:\/\/platform.claude.com\/docs\/en\/about-claude\/pricing. Accessed: 2026-02-28."},{"key":"e_1_3_3_2_3_2","unstructured":"Peter Belcak Greg Heinrich Shizhe Diao Yonggan Fu Xin Dong Saurav Muralidharan Yingyan\u00a0Celine Lin and Pavlo Molchanov. 2025. Small Language Models are the Future of Agentic AI. arxiv:https:\/\/arXiv.org\/abs\/2506.02153\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2506.02153"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_3_2_5_2","unstructured":"Cooper Elsworth Keguo Huang David Patterson Ian Schneider Robert Sedivy Savannah Goodman Ben Townsend Parthasarathy Ranganathan Jeff Dean Amin Vahdat Ben Gomes and James Manyika. 2025. Measuring the environmental impact of delivering AI at Google Scale. arxiv:https:\/\/arXiv.org\/abs\/2508.15734\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2508.15734"},{"key":"e_1_3_3_2_6_2","unstructured":"ggml.ai. n. d.. Llama.cpp. https:\/\/github.com\/ggml-org\/llama.cpp"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0037"},{"key":"e_1_3_3_2_8_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Gupta Neha","year":"2024","unstructured":"Neha Gupta, Harikrishna Narasimhan, Wittawat Jitkrittum, Ankit\u00a0Singh Rawat, Aditya\u00a0Krishna Menon, and Sanjiv Kumar. 2024. Language Model Cascades: Token-Level Uncertainty And Beyond. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=KgaBScZ4VI"},{"key":"e_1_3_3_2_9_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Jimenez Carlos\u00a0E","year":"2024","unstructured":"Carlos\u00a0E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik\u00a0R Narasimhan. 2024. SWE-bench: Can Language Models Resolve Real-world Github Issues?. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=VTF8yNQM66"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3229434.3229441"},{"key":"e_1_3_3_2_11_2","unstructured":"Jiin Kim Byeongjun Shin Jinha Chung and Minsoo Rhu. 2025. The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.04301 (2025)."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.243"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3690668"},{"key":"e_1_3_3_2_14_2","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Li Yilong","year":"2025","unstructured":"Yilong Li, Jingyu Liu, Hao Zhang, M\u00a0Badri Narayanan, Utkarsh Sharma, Shuai Zhang, Yijing Zeng, Jayaram Raghuram, and Suman Banerjee. 2025. PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=xzSUdw6s76"},{"key":"e_1_3_3_2_15_2","unstructured":"Zhen Lin Shubhendu Trivedi and Jimeng Sun. 2024. Generating with Confidence: Uncertainty Quantification for Black-box Large Language Models. Transactions on Machine Learning Research (2024). https:\/\/openreview.net\/forum?id=DWkJCSxKU5"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.1304"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.718"},{"key":"e_1_3_3_2_18_2","series-title":"(NIPS \u201923)","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"McElfresh Duncan","year":"2023","unstructured":"Duncan McElfresh, Sujay Khandagale, Jonathan Valverde, Vishak\u00a0Prasad C., Ganesh Ramakrishnan, Micah Goldblum, and Colin White. 2023. When do neural nets outperform boosted trees on tabular data?. In Proceedings of the 37th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS \u201923). Curran Associates Inc., Red Hook, NY, USA, Article 3337, 34\u00a0pages."},{"key":"e_1_3_3_2_19_2","unstructured":"OpenAI. 2026. OpenAI API Pricing. https:\/\/openai.com\/api\/pricing\/. Accessed: 2026-02-28."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"David Patterson Jeffrey\u00a0M. Gilbert Marco Gruteser Efren Robles Krishna Sekar Yong Wei and Tenghui Zhu. 2024. Energy and Emissions of Machine Learning on Smartphones vs. the Cloud. Commun. ACM 67 2 (Jan. 2024) 86\u201397. 10.1145\/36247193624719\"\/>","DOI":"10.1145\/3624719"},{"key":"e_1_3_3_2_21_2","unstructured":"Qwen. 2025. Qwen3 Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2505.09388\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2505.09388"},{"key":"e_1_3_3_2_22_2","unstructured":"Aymeric Roucher Albert\u00a0Villanova del Moral Thomas Wolf Leandro von Werra and Erik Kaunism\u00e4ki. 2025. \u2018smolagents\u2018: a smol library to build great agentic systems. https:\/\/github.com\/huggingface\/smolagents."},{"key":"e_1_3_3_2_23_2","unstructured":"Jon Saad-Falcon Avanika Narayan Hakki\u00a0Orhun Akengin J.\u00a0Wes Griffin Herumb Shandilya Adrian\u00a0Gamarra Lafuente Medhya Goel Rebecca Joseph Shlok Natarajan Etash\u00a0Kumar Guha Shang Zhu Ben Athiwaratkun John Hennessy Azalia Mirhoseini and Christopher R\u00e9. 2025. Intelligence per Watt: Measuring Intelligence Efficiency of Local AI. arxiv:https:\/\/arXiv.org\/abs\/2511.07885\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2511.07885"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSC61953.2024.10603302"},{"key":"e_1_3_3_2_25_2","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc\u00a0V. Le, Geoffrey\u00a0E. Hinton, and Jeff Dean. 2017. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=B1ckMDqlg"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.189"},{"key":"e_1_3_3_2_27_2","series-title":"(ICML\u201924)","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Wang Xingyao","year":"2024","unstructured":"Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, and Heng Ji. 2024. Executable code actions elicit better LLM agents. In Proceedings of the 41st International Conference on Machine Learning (Vienna, Austria) (ICML\u201924). JMLR.org, Article 2054, 25\u00a0pages."},{"key":"e_1_3_3_2_28_2","unstructured":"Jason Wei Nguyen Karina Hyung\u00a0Won Chung Yunxin\u00a0Joy Jiao Spencer Papay Amelia Glaese John Schulman and William Fedus. 2024. Measuring short-form factuality in large language models. arxiv:https:\/\/arXiv.org\/abs\/2411.04368\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2411.04368"},{"key":"e_1_3_3_2_29_2","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Yang John","year":"2024","unstructured":"John Yang, Carlos\u00a0E Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik\u00a0R Narasimhan, and Ofir Press. 2024. SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/arxiv.org\/abs\/2405.15793"},{"key":"e_1_3_3_2_30_2","volume-title":"The Eleventh International Conference on Learning Representations","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik\u00a0R Narasimhan, and Yuan Cao. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=WE_vluYUL-X"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Caglar Yildirim and Ana-Paula Correia. 2015. Exploring the dimensions of nomophobia: Development and validation of a self-reported questionnaire. Computers in human behavior 49 (2015) 130\u2013137.","DOI":"10.1016\/j.chb.2015.02.059"},{"key":"e_1_3_3_2_32_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yue Murong","year":"2024","unstructured":"Murong Yue, Jie Zhao, Min Zhang, Liang Du, and Ziyu Yao. 2024. Large Language Model Cascades with Mixture of Thought Representations for Cost-Efficient Reasoning. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=6okaSfANzh"},{"key":"e_1_3_3_2_33_2","unstructured":"Michael\u00a0J. Zellinger Rex Liu and Matt Thomson. 2025. Cost-Saving LLM Cascades with Early Abstention. arxiv:https:\/\/arXiv.org\/abs\/2502.09054\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2502.09054"},{"key":"e_1_3_3_2_34_2","series-title":"(NIPS \u201920)","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Zhou Wangchunshu","year":"2020","unstructured":"Wangchunshu Zhou, Canwen Xu, Tao Ge, Julian McAuley, Ke Xu, and Furu Wei. 2020. BERT loses patience: fast and robust inference with early exit. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS \u201920). Curran Associates Inc., Red Hook, NY, USA, Article 1539, 12\u00a0pages."},{"key":"e_1_3_3_2_35_2","volume-title":"The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Zhu Yuxuan","year":"2025","unstructured":"Yuxuan Zhu, Tengjun Jin, Yada Pruksachatkun, Andy\u00a0K Zhang, Shu Liu, Sasha Cui, Sayash Kapoor, Shayne Longpre, Kevin Meng, Rebecca Weiss, Fazl Barez, Rahul Gupta, Jwala Dhamala, Jacob Merizian, Mario Giulianelli, Harry Coppock, Cozmin Ududec, Antony Kellermann, Jasjeet\u00a0S Sekhon, Jacob Steinhardt, Sarah Schwettmann, Arvind Narayanan, Matei Zaharia, Ion Stoica, Percy Liang, and Daniel Kang. 2025. Establishing Best Practices in Building Rigorous Agentic Benchmarks. In The Thirty-ninth Annual Conference on Neural Information Processing Systems Datasets and Benchmarks Track. https:\/\/openreview.net\/forum?id=E58HNCqoaA"}],"event":{"name":"CAIS '26: ACM Conference on AI and Agentic Systems","location":"San Jose CA USA","acronym":"CAIS '26"},"container-title":["Proceedings of the ACM Conference on AI and Agentic Systems"],"original-title":[],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T03:24:45Z","timestamp":1779420285000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786335.3813163"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,26]]},"references-count":34,"alternative-id":["10.1145\/3786335.3813163","10.1145\/3786335"],"URL":"https:\/\/doi.org\/10.1145\/3786335.3813163","relation":{},"subject":[],"published":{"date-parts":[[2026,5,26]]},"assertion":[{"value":"2026-05-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}