{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T04:07:46Z","timestamp":1779422866748,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":20,"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"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2112562"],"award-info":[{"award-number":["CNS-2112562"]}],"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":[[2026,5,26]]},"DOI":"10.1145\/3786335.3813205","type":"proceedings-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T03:16:22Z","timestamp":1779419782000},"page":"1248-1252","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Skilled AI Agents for Embedded and IoT Systems Development"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7648-9213","authenticated-orcid":false,"given":"Yiming","family":"Li","sequence":"first","affiliation":[{"name":"Duke University, Durham, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7731-2780","authenticated-orcid":false,"given":"Yuhan","family":"Cheng","sequence":"additional","affiliation":[{"name":"Duke University, Durham, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1199-7176","authenticated-orcid":false,"given":"Mingchen","family":"Ma","sequence":"additional","affiliation":[{"name":"Duke University, Durham, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6698-5439","authenticated-orcid":false,"given":"Yihang","family":"Zou","sequence":"additional","affiliation":[{"name":"Duke University, Durham, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0144-3644","authenticated-orcid":false,"given":"Ningyuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Duke University, Durham, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1281-9243","authenticated-orcid":false,"given":"Wei","family":"Cheng","sequence":"additional","affiliation":[{"name":"Duke University, Durham, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3228-6544","authenticated-orcid":false,"given":"Hai","family":"Li","sequence":"additional","affiliation":[{"name":"Duke University, Durham, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1486-8412","authenticated-orcid":false,"given":"Yiran","family":"Chen","sequence":"additional","affiliation":[{"name":"Duke University, Durham, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5717-5755","authenticated-orcid":false,"given":"Tingjun","family":"Chen","sequence":"additional","affiliation":[{"name":"Duke University, Durham, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,26]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"2025. Agent Skills are a simple open format for giving agents new capabilities and expertise. https:\/\/github.com\/agentskills\/agentskills."},{"key":"e_1_3_3_1_3_2","unstructured":"2026. Skilled AI Agents for Embedded and IoT Systems Development. https:\/\/github.com\/iot-agent."},{"key":"e_1_3_3_1_4_2","unstructured":"Lingjiao Chen Matei Zaharia and James Zou. 2023. Frugalgpt: How to use large language models while reducing cost and improving performance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.05176 (2023)."},{"key":"e_1_3_3_1_5_2","unstructured":"CodeMagic LTD. 2026. Wokwi Simulator. https:\/\/wokwi.com\/."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3711875.3729136"},{"key":"e_1_3_3_1_7_2","unstructured":"Naman Jain King Han Alex Gu Wen-Ding Li Fanjia Yan Tianjun Zhang Sida Wang Armando Solar-Lezama Koushik Sen and Ion Stoica. 2024. Livecodebench: Holistic and contamination free evaluation of large language models for code. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.07974 (2024)."},{"key":"e_1_3_3_1_8_2","unstructured":"Carlos\u00a0E Jimenez John Yang Alexander Wettig Shunyu Yao Kexin Pei Ofir Press and Karthik Narasimhan. 2023. SWE-Bench: Can Language Models Resolve Real-World GitHub Issues? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.06770 (2023)."},{"key":"e_1_3_3_1_9_2","unstructured":"LangChain Inc. 2026. LangGraph: Low-Level Orchestration Framework for Building Managing and Deploying Long-Running Stateful Agents. https:\/\/github.com\/langchain-ai\/langgraph."},{"key":"e_1_3_3_1_10_2","unstructured":"Xiangyi Li Wenbo Chen Yimin Liu Shenghan Zheng Xiaokun Chen Yifeng He Yubo Li Bingran You Haotian Shen Jiankai Sun et\u00a0al. 2026. SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2602.12670 (2026)."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715014.3722070"},{"key":"e_1_3_3_1_12_2","unstructured":"QEMU Project. 2026. QEMU: A Generic and Open Source Machine Emulator and Virtualizer. https:\/\/www.qemu.org\/."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715014.3722064"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3680207.3723486"},{"key":"e_1_3_3_1_15_2","unstructured":"Yang Song Anoushka Vyas Zirui Wei Sina\u00a0Khoshfetrat Pakazad Henrik Ohlsson and Graham Neubig. 2026. NEMO: Execution-Aware Optimization Modeling via Autonomous Coding Agents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2601.21372 (2026)."},{"key":"e_1_3_3_1_16_2","unstructured":"Nandan Thakur Jimmy Lin Sam Havens Michael Carbin Omar Khattab and Andrew Drozdov. 2025. Freshstack: Building realistic benchmarks for evaluating retrieval on technical documents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.13128 (2025)."},{"key":"e_1_3_3_1_17_2","unstructured":"Ruiyang Xu Jialun Cao Mingyuan Wu Wenliang Zhong Yaojie Lu Ben He Xianpei Han Shing-Chi Cheung and Le Sun. 2025. EmbedAgent: Benchmarking Large Language Models in Embedded System Development. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.11003 (2025)."},{"key":"e_1_3_3_1_18_2","unstructured":"Huanqi Yang Mingzhe Li Mingda Han Zhenjiang Li and Weitao Xu. 2024. EmbedGenius: Towards Automated Software Development for Generic Embedded IoT Systems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.09058 (2024)."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"John Yang Carlos\u00a0E Jimenez Alexander Wettig Kilian Lieret Shunyu Yao Karthik Narasimhan and Ofir Press. 2024. SWE-Agent: Agent-Computer Interfaces Enable Automated Software Engineering. Adv. Neural Inf. Process. Syst. 37 (2024) 50528\u201350652.","DOI":"10.52202\/079017-1601"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3737895.3768303"},{"key":"e_1_3_3_1_21_2","unstructured":"Terry\u00a0Yue Zhuo Minh\u00a0Chien Vu Jenny Chim Han Hu Wenhao Yu Ratnadira Widyasari Imam Nur\u00a0Bani Yusuf Haolan Zhan Junda He Indraneil Paul et\u00a0al. 2024. BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.15877 (2024)."}],"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":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3786335.3813205","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T03:27:13Z","timestamp":1779420433000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786335.3813205"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,26]]},"references-count":20,"alternative-id":["10.1145\/3786335.3813205","10.1145\/3786335"],"URL":"https:\/\/doi.org\/10.1145\/3786335.3813205","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"}}]}}