{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T15:41:03Z","timestamp":1769010063384,"version":"3.49.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2324854"],"award-info":[{"award-number":["2324854"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,31]]},"DOI":"10.23919\/date64628.2025.10992798","type":"proceedings-article","created":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T17:36:35Z","timestamp":1747848995000},"page":"1-7","source":"Crossref","is-referenced-by-count":7,"title":["Less is More: Optimizing Function Calling for LLM Execution on Edge Devices"],"prefix":"10.23919","author":[{"given":"Varatheepan","family":"Paramanayakam","sequence":"first","affiliation":[{"name":"School of Electrical, Computer and Biomedical Engineering, Southern Illinois University,Carbondale,IL,U.S.A."}]},{"given":"Andreas","family":"Karatzas","sequence":"additional","affiliation":[{"name":"School of Electrical, Computer and Biomedical Engineering, Southern Illinois University,Carbondale,IL,U.S.A."}]},{"given":"Iraklis","family":"Anagnostopoulos","sequence":"additional","affiliation":[{"name":"School of Electrical, Computer and Biomedical Engineering, Southern Illinois University,Carbondale,IL,U.S.A."}]},{"given":"Dimitrios","family":"Stamoulis","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin,Department of Electrical and Computer Engineering,Austin,TX,U.S.A."}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gorilla: Large language model connected with massive apis","author":"Patil","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Llm inference unveiled: Survey and roofline model insights","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Function calling documentation","volume-title":"OpenAI"},{"key":"ref4","article-title":"ReAct: Synergizing reasoning and acting in language models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Yao","year":"2023"},{"key":"ref5","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Function calling","volume-title":"HuggingFace","year":"2024"},{"key":"ref7","article-title":"Tool support","volume-title":"Ollama","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-demo.9"},{"key":"ref9","volume-title":"Berkeley function calling leaderboard","author":"Yan","year":"2024"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00063"},{"key":"ref11","volume-title":"Nvidia jetson agx orin series","author":"Karumbunathan","year":"2022"},{"key":"ref12","article-title":"Qlora: Efficient finetuning of quantized llms","volume":"36","author":"Dettmers","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","first-page":"21 702","article-title":"Llm-pruner: On the structural pruning of large language models","volume":"36","author":"Ma","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref15","article-title":"MiniLLM: Knowledge distillation of large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Gu","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.825"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.678"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2024.3375352"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651335"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC62836.2024.10938426"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3658473"},{"key":"ref22","article-title":"Routerbench: A benchmark for multi-llm routing system","author":"Hu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Frugalgpt: How to use large language models while reducing cost and improving performance","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.50"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICECS61496.2024.10848749"},{"key":"ref26","article-title":"Memserve: Context caching for disaggregated llm serving with elastic memory pool","author":"Hu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"ToolLLM: Facilitating large language models to master 16000+ real-world APIs","volume-title":"The Twelfth International Conference on Learning Representations","author":"Qin","year":"2024"},{"key":"ref28","article-title":"Octopus: On-device language model for function calling of software apis","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"An llm compiler for parallel function calling","author":"Kim","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"An llm-tool compiler for fused parallel function calling","author":"Singh","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Contextual retrieval","volume-title":"Anthropic","year":"2024"},{"key":"ref32","first-page":"16857","article-title":"Mpnet: Masked and permuted pretraining for language understanding","volume":"33","author":"Song","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref33","first-page":"50117","article-title":"Toolqa: A dataset for llm question answering with external tools","volume":"36","author":"Zhuang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","article-title":"Agglomerative clustering","volume-title":"scikit learn","year":"2024"},{"key":"ref35","volume-title":"The faiss library","author":"Douze","year":"2024"},{"key":"ref36","article-title":"Hermes-2-pro-llama-3\u20138b","volume-title":"NousResearch"},{"key":"ref37","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Mistral 7b","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 Design, Automation & Test in Europe Conference (DATE)","location":"Lyon, France","start":{"date-parts":[[2025,3,31]]},"end":{"date-parts":[[2025,4,2]]}},"container-title":["2025 Design, Automation & Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10992638\/10992588\/10992798.pdf?arnumber=10992798","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T05:32:18Z","timestamp":1747891938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10992798\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":39,"URL":"https:\/\/doi.org\/10.23919\/date64628.2025.10992798","relation":{},"subject":[],"published":{"date-parts":[[2025,3,31]]}}}