{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T07:09:46Z","timestamp":1771571386036,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T00:00:00Z","timestamp":1764028800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T00:00:00Z","timestamp":1764028800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,11,25]]},"DOI":"10.1109\/fllm67465.2025.11391052","type":"proceedings-article","created":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T20:55:46Z","timestamp":1771534546000},"page":"1267-1274","source":"Crossref","is-referenced-by-count":0,"title":["Performance and Cost Optimization of Federated LLM Agents in Edge Computing Environments"],"prefix":"10.1109","author":[{"given":"Goutam","family":"Tadi","sequence":"first","affiliation":[{"name":"Astronomer,Platform Engineering,Leander,TX,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Akshay","family":"Mittal","sequence":"additional","affiliation":[{"name":"University of the Cumberlands,Austin,TX,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3166101"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref3","article-title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"McMahan"},{"key":"ref4","article-title":"Federated Optimization in Heterogeneous Networks","volume-title":"Proceedings of Machine Learning and Systems (MLSys)","author":"Li"},{"key":"ref5","article-title":"Orca: A Distributed Serving System for Transformer-Based Generative Models","volume-title":"Proceedings of the 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI \u201922)","author":"Yu"},{"key":"ref6","article-title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML)","author":"Frantar"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1145\/3714983.3714987","article-title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","volume-title":"Proceedings of Machine Learning and Systems (MLSys)","author":"Lin"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2018.1700175"},{"key":"ref9","first-page":"1","article-title":"Flower: A friendly federated learning research framework","volume-title":"Proceedings of Machine Learning and Systems (MLSys)","volume":"4","author":"Beutel"},{"key":"ref10","article-title":"Reconfigurable Architectures for Data Analytics on Next-Generation Edge-Computing Platforms","author":"Perera","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3061981"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2918951"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/mwc.009.2400244"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/besc48373.2019.8962995"},{"key":"ref16","article-title":"Adaptive Federated Optimization","volume-title":"International Conference on Learning Representations (ICLR)","author":"Reddi"},{"key":"ref17","article-title":"Towards Federated Learning at Scale: System Design","volume-title":"Proceedings of the 2nd SysML Conference","author":"Bonawitz"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2023.3285868"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2024.3461852"},{"key":"ref21","article-title":"LEAF: A Benchmark for Federated Settings","volume-title":"Proceedings of the 33rd Conference on Neural Information Processing Systems","author":"Caldas"},{"issue":"2","key":"ref22","first-page":"456","article-title":"Evaluating the energy impact of device and workload parameters for DNN inference on edge","volume":"8","author":"Dutt","year":"2023","journal-title":"IEEE Transactions on Sustainable Computing"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ispa-bdcloud-socialcom-sustaincom52081.2021.00209"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50371-0_16"},{"key":"ref25","volume-title":"Edge Computing Systems with Kubernetes: A use case guide for building edge systems using K3s, k3OS, and open source cloud native technologies","author":"M\u00e9ndez","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765695"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref28","first-page":"1877","article-title":"Language Models are Few-Shot Learners","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Brown"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid54584.2022.00102"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/sose67019.2025.00014"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50371-0_16"},{"issue":"2","key":"ref32","first-page":"456","article-title":"Evaluating the energy impact of device and workload parameters for DNN inference on edge","volume":"8","author":"Dutt","year":"2023","journal-title":"IEEE Transactions on Sustainable Computing"}],"event":{"name":"2025 3rd International Conference on Foundation and Large Language Models (FLLM)","location":"Vienna, Austria","start":{"date-parts":[[2025,11,25]]},"end":{"date-parts":[[2025,11,28]]}},"container-title":["2025 3rd International Conference on Foundation and Large Language Models (FLLM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11390736\/11390873\/11391052.pdf?arnumber=11391052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T06:42:15Z","timestamp":1771569735000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11391052\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,25]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/fllm67465.2025.11391052","relation":{},"subject":[],"published":{"date-parts":[[2025,11,25]]}}}