{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:28:06Z","timestamp":1778758086971,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":11,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T00:00:00Z","timestamp":1776902400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS 1911012"],"award-info":[{"award-number":["CNS 1911012"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS 2124908"],"award-info":[{"award-number":["CNS 2124908"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF 213543"],"award-info":[{"award-number":["CCF 213543"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,23]]},"DOI":"10.1145\/3746467.3801501","type":"proceedings-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:06:32Z","timestamp":1778756792000},"page":"264-269","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["iGenOrch: Intelligent Orchestration Framework for Multi-Model LLM Inference on Edge Platforms"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-7134-7405","authenticated-orcid":false,"given":"Faiza","family":"Akram","sequence":"first","affiliation":[{"name":"Mississippi State University, Starkville, MS, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0693-8696","authenticated-orcid":false,"given":"Maisha Rahman","family":"Chowdhury","sequence":"additional","affiliation":[{"name":"Iowa State University, Ames, IA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5285-9386","authenticated-orcid":false,"given":"Gabriella","family":"Dunne","sequence":"additional","affiliation":[{"name":"Benedictine College, Atchison, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5660-3625","authenticated-orcid":false,"given":"Katherine","family":"Williams","sequence":"additional","affiliation":[{"name":"Washington and Lee University, Lexington, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6758-6982","authenticated-orcid":false,"given":"Kaleb","family":"Love","sequence":"additional","affiliation":[{"name":"Mississippi State University, Starkville, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3804-997X","authenticated-orcid":false,"given":"Asad Waqar","family":"Malik","sequence":"additional","affiliation":[{"name":"Mississippi State University, Starkville, Mississippi, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6641-9735","authenticated-orcid":false,"given":"Samee U.","family":"Khan","sequence":"additional","affiliation":[{"name":"Kansas State University, Manhattan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,14]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et al. 2023. GPT-4 Technical Report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Language Models are Few-Shot Learners. arXiv preprint arXiv:2005.14165","author":"Brown Tom B","year":"2020","unstructured":"Tom B Brown. 2020. Language Models are Few-Shot Learners. arXiv preprint arXiv:2005.14165 (2020)."},{"key":"e_1_3_2_1_3_1","unstructured":"IBM Developer. 2023. Completely Fair Scheduler. https:\/\/developer.ibm.com\/tutorials\/l-completely-fair-scheduler\/"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of machine learning and systems 6","author":"Lin Ji","year":"2024","unstructured":"Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, and Song Han. 2024. AWQ: Activation-Aware Weight Quantization for On-Device LLM Compression and Acceleration. Proceedings of machine learning and systems 6 (2024), 87\u2013100."},{"key":"e_1_3_2_1_5_1","first-page":"62432","article-title":"The Mamba in the Llama: Distilling and Accelerating Hybrid Models","volume":"37","author":"Wang Junxiong","year":"2024","unstructured":"Junxiong Wang, Daniele Paliotta, Avner May, Alexander Rush, and Tri Dao. 2024. The Mamba in the Llama: Distilling and Accelerating Hybrid Models. Advances in Neural Information Processing Systems 37 (2024), 62432\u201362457.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3700410.3702126"},{"key":"e_1_3_2_1_7_1","unstructured":"Jason Wei Yi Tay Rishi Bommasani Colin Raffel Barret Zoph Sebastian Borgeaud Dani Yogatama Maarten Bosma Denny Zhou Donald Metzler et al. 2022. Emergent Abilities of Large Language Models. arXiv preprint arXiv:2206.07682 (2022)."},{"key":"e_1_3_2_1_8_1","volume-title":"Efficient Scheduling of Agentic LLM Workloads on Heterogeneous SoC. arXiv preprint arXiv:2506.24045","author":"Wei Xinming","year":"2025","unstructured":"Xinming Wei, Jiahao Zhang, Haoran Li, Jiayu Chen, Rui Qu, Maoliang Li, Xiang Chen, and Guojie Luo. 2025. Agent.xpu: Efficient Scheduling of Agentic LLM Workloads on Heterogeneous SoC. arXiv preprint arXiv:2506.24045 (2025)."},{"key":"e_1_3_2_1_9_1","volume-title":"On-Device Language Models: A Comprehensive Review. arXiv preprint arXiv:2409.00088","author":"Xu Jiajun","year":"2024","unstructured":"Jiajun Xu, Zhiyuan Li, Wei Chen, Qun Wang, Xin Gao, Qi Cai, and Ziyuan Ling. 2024. On-Device Language Models: A Comprehensive Review. arXiv preprint arXiv:2409.00088 (2024)."},{"key":"e_1_3_2_1_10_1","volume-title":"LLM as a System Service on Mobile Devices. arXiv preprint arXiv:2403.11805","author":"Yin Wangsong","year":"2024","unstructured":"Wangsong Yin, Mengwei Xu, Yuanchun Li, and Xuanzhe Liu. 2024. LLM as a System Service on Mobile Devices. arXiv preprint arXiv:2403.11805 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"Tinyllama: An Open-Source Small Language Model. arXiv preprint arXiv:2401.02385","author":"Zhang Peiyuan","year":"2024","unstructured":"Peiyuan Zhang, Guangtao Zeng, Tianduo Wang, and Wei Lu. 2024. Tinyllama: An Open-Source Small Language Model. arXiv preprint arXiv:2401.02385 (2024)."}],"event":{"name":"ACMSE 2026: 2026 ACM Southeast Conference","location":"Troy University Troy AL USA","acronym":"ACMSE 2026"},"container-title":["Proceedings of the 2026 ACM Southeast Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746467.3801501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:06:50Z","timestamp":1778756810000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746467.3801501"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,23]]},"references-count":11,"alternative-id":["10.1145\/3746467.3801501","10.1145\/3746467"],"URL":"https:\/\/doi.org\/10.1145\/3746467.3801501","relation":{},"subject":[],"published":{"date-parts":[[2026,4,23]]},"assertion":[{"value":"2026-05-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}