{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T05:57:39Z","timestamp":1781675859063,"version":"3.54.5"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62431013,62301077"],"award-info":[{"award-number":["62431013,62301077"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1109\/wcnc65185.2026.11555243","type":"proceedings-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T19:41:29Z","timestamp":1781638889000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Drift-Plus-Penalty Based Queue Management for Edge LLM Inference with Repeated Sampling"],"prefix":"10.1109","author":[{"given":"Hongtao","family":"Li","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengxian","family":"Guo","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruihong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mugen","family":"Peng","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,State Key Laboratory of Networking and Switching Technology,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/mcom.001.2400764"},{"key":"ref2","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2025.3546256"},{"key":"ref4","article-title":"Splitllm: Collaborative inference of 11 ms for model placement and throughput optimization","author":"Mudvari","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3513457"},{"key":"ref6","article-title":"Networks of networks: Complexity class principles applied to compound ai systems design","author":"Davis","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Large language monkeys: Scaling inference compute with repeated sampling","author":"Brown","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Inference scaling laws: An empirical analysis of compute-optimal inference for problemsolving with language models","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Scaling llm test-time compute optimally can be more effective than scaling model parameters","author":"Snell","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Multi-bin batching for increasing 11 m inference throughput","author":"Guldogan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","first-page":"273","article-title":"A queueing theoretic perspective on low-latency 11 m inference with variable token length","volume-title":"2024 22nd International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt). IEEE","author":"Yang"},{"key":"ref12","article-title":"Optimizing llm inference throughput via memory-aware and sla-constrained dynamic batching","author":"Pang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref13","volume-title":"Introduction to probability models","author":"Ross","year":"2014"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-79995-2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2012.2204831"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.peva.2012.10.003"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.peva.2020.102183"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2025.3526283"}],"event":{"name":"2026 IEEE Wireless Communications and Networking Conference (WCNC)","location":"Kuala Lumpur, Malaysia","start":{"date-parts":[[2026,4,13]]},"end":{"date-parts":[[2026,4,16]]}},"container-title":["2026 IEEE Wireless Communications and Networking Conference (WCNC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11555037\/11555040\/11555243.pdf?arnumber=11555243","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T05:39:03Z","timestamp":1781674743000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11555243\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/wcnc65185.2026.11555243","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]}}}