{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T05:06:13Z","timestamp":1741323973977,"version":"3.38.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3544637","type":"journal-article","created":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T18:41:32Z","timestamp":1740422492000},"page":"37522-37533","source":"Crossref","is-referenced-by-count":0,"title":["Small Language Model Agent for the Operations of Continuously Updating ICT Systems"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7846-1717","authenticated-orcid":false,"given":"Nobukazu","family":"Fukuda","sequence":"first","affiliation":[{"name":"NTT Access Network Service Systems Laboratories, NTT Corporation, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9653-8221","authenticated-orcid":false,"given":"Haruhisa","family":"Nozue","sequence":"additional","affiliation":[{"name":"NTT Access Network Service Systems Laboratories, NTT Corporation, Tokyo, Japan"}]},{"given":"Haruo","family":"Oishi","sequence":"additional","affiliation":[{"name":"NTT Access Network Service Systems Laboratories, NTT Corporation, Tokyo, Japan"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref2","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref3","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref4","article-title":"LLaMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3274199"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3325727"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3397326"},{"key":"ref8","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wei"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40231-1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161317"},{"article-title":"Voyager: An open-ended embodied agent with large language models","volume-title":"Proc. Intrinsically-Motivated Open-Ended Learn. Workshop @NeurIPS","author":"Wang","key":"ref11"},{"article-title":"Synapse: Trajectory-as-exemplar prompting with memory for computer control","volume-title":"Proc. NeurIPS Found. Models Decis. Making Workshop","author":"Zheng","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663841"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3542929.3563482"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00149"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629553"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.14778\/3675034.3675043"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3698038.3698525"},{"key":"ref19","article-title":"Mistral 7B","author":"Jiang","year":"2023","journal-title":"arXiv:2310.06825"},{"key":"ref20","article-title":"Gemma: Open models based on Gemini research and technology","author":"Mesnard","year":"2024","journal-title":"arXiv:2403.08295"},{"article-title":"AgentBench: Evaluating LLMs as agents","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Liu","key":"ref21"},{"article-title":"SteP: Stacked LLM policies for web actions","volume-title":"Proc. 1st Conf. Lang. Model.","author":"Sodhi","key":"ref22"},{"key":"ref23","article-title":"Understanding the planning of LLM agents: A survey","author":"Huang","year":"2024","journal-title":"arXiv:2402.02716"},{"article-title":"ReAct: Synergizing reasoning and acting in language models","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Yao","key":"ref24"},{"article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"Proc. 6th Annu. Conf. Robot Learn.","author":"Huang","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.181"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.352"},{"key":"ref28","article-title":"WebGPT: Browser-assisted question-answering with human feedback","author":"Nakano","year":"2021","journal-title":"arXiv:2112.09332"},{"key":"ref29","first-page":"9118","article-title":"Language models as zero-shot planners: Extracting actionable knowledge for embodied agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref30","article-title":"FeUdal networks for hierarchical reinforcement learning","author":"Vezhnevets","year":"2017","journal-title":"arXiv:1703.01161"},{"key":"ref31","first-page":"3307","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Nachum"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.147"},{"article-title":"Tree of thoughts: Deliberate problem solving with large language models","volume-title":"Proc. 27th Conf. Neural Inf. Process. Syst.","author":"Yao","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"},{"article-title":"Thought propagation: An analogical approach to complex reasoning with large language models","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Yu","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.264"},{"article-title":"Generating sequences by learning to self-correct","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Welleck","key":"ref37"},{"key":"ref38","first-page":"46534","article-title":"Self-refine: Iterative refinement with self-feedback","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Madaan"},{"key":"ref39","first-page":"8634","article-title":"Reflexion: Language agents with verbal reinforcement learning","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Shinn"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29936"},{"key":"ref41","article-title":"RAP: Retrieval-augmented planning with contextual memory for multimodal LLM agents","author":"Kagaya","year":"2024","journal-title":"arXiv:2402.03610"},{"key":"ref42","first-page":"287","article-title":"An instance-based state representation for network repair","volume-title":"Proc. Nat. Conf. Artif. Intell.","author":"Littman"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2007.11"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098190"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS47738.2020.9110370"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3663529.3663858"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3680016"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-SEIP.2019.00021"},{"key":"ref49","first-page":"50208","article-title":"Executable code actions elicit better LLM agents","volume-title":"Proc. Workshop Large Lang. Model (LLM) Agents","author":"Wang"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.284"},{"article-title":"ALFWorld: Aligning text and embodied environments for interactive learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Shridhar","key":"ref51"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-24337-1_3"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639081"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.493"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3000405"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2200012"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10900353.pdf?arnumber=10900353","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T06:05:11Z","timestamp":1741241111000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10900353\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3544637","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}