{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T07:25:44Z","timestamp":1787210744054,"version":"build-2736575974"},"reference-count":57,"publisher":"World Scientific Pub Co Pte Ltd","issue":"03","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Semantic Computing"],"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:p>Large language models (LLMs) have significantly advanced semantic computing by enabling systems to interpret and generate natural language with high flexibility. However, they remain limited in solving real-world problems that require precise computation, reliable data access, and structured optimization. Tasks such as route planning, geospatial reasoning, and combinatorial optimization highlight these shortcomings, particularly in terms of factual grounding and solution feasibility. This paper proposes a framework for tool-augmented semantic computing, in which LLMs are combined with external data sources and specialized algorithmic components. The framework consists of a semantic layer for interpreting user intent, a tool layer for data access and computation, and an orchestration layer coordinating their interaction. By using travel planning as a representative use case, we demonstrate how tasks such as point-of-interest selection, coordinate retrieval, and route optimization can be decomposed into modular processing steps. In particular, route sequencing is formulated as a variant of the traveling salesman problem, requiring dedicated optimization beyond the capabilities of LLMs. The results show that integrating semantic reasoning with data grounding and algorithmic optimization enables reliable solutions to complex real-world problems, highlighting the potential of hybrid AI systems for future semantic computing applications.<\/jats:p>","DOI":"10.1142\/s1793351x26430014","type":"journal-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T05:03:43Z","timestamp":1783659823000},"page":"301-326","source":"Crossref","is-referenced-by-count":0,"title":["Toward Tool\u2013Augmented Semantic Computing: Integrating Large Language Models with Data Grounding and Optimization for Real\u2013World Problem Solving"],"prefix":"10.1142","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7941-1042","authenticated-orcid":false,"given":"Florian","family":"Schimanke","sequence":"first","affiliation":[{"name":"Department of Computer Science, HSW \u2014 University of Applied Sciences, Am Stockhof 2, 31785 Hameln, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9974-2666","authenticated-orcid":false,"given":"Maren","family":"Schnieder","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, Bochum University of Applied Sciences, Am Hochschul Campus 1, 44801 Bochum, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2414-4584","authenticated-orcid":false,"given":"Robert","family":"Mertens","sequence":"additional","affiliation":[{"name":"Department of Computer Science, HSW \u2014 University of Applied Sciences, Am Stockhof 2, 31785 Hameln, Germany"},{"name":"BHH University of Applied Sciences, Anckelmannstra\u00dfe 10, 20537 Hamburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9242-0348","authenticated-orcid":false,"given":"Alessandro","family":"Pio","sequence":"additional","affiliation":[{"name":"University of L\u2019Aquila, L\u2019Aquila, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1798-0215","authenticated-orcid":false,"given":"Fabio","family":"Persia","sequence":"additional","affiliation":[{"name":"University of L\u2019Aquila, L\u2019Aquila, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6254-2249","authenticated-orcid":false,"given":"Giovanni","family":"Pilato","sequence":"additional","affiliation":[{"name":"National Research Council of Italy, Palermo, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4107-5303","authenticated-orcid":false,"given":"Mouzhi","family":"Ge","sequence":"additional","affiliation":[{"name":"Deggendorf Institute of Technology, Deggendorf, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7056-4245","authenticated-orcid":false,"given":"Mustafa","family":"Sert","sequence":"additional","affiliation":[{"name":"Department of EECS, University of California, Irvine, CA, USA"},{"name":"Department of Artificial Intelligence Engineering, Ba\u015fkent University, Ankara, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"219","published-online":{"date-parts":[[2026,7,30]]},"reference":[{"key":"S1793351X26430014BIB001","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121375"},{"key":"S1793351X26430014BIB002","doi-asserted-by":"publisher","DOI":"10.3390\/su13179771"},{"key":"S1793351X26430014BIB003","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2025.1632766"},{"key":"S1793351X26430014BIB004","doi-asserted-by":"publisher","DOI":"10.1145\/3678717.3691305"},{"key":"S1793351X26430014BIB005","doi-asserted-by":"publisher","DOI":"10.3390\/math13020221"},{"key":"S1793351X26430014BIB006","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2026.104448"},{"key":"S1793351X26430014BIB007","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071"},{"key":"S1793351X26430014BIB008","doi-asserted-by":"publisher","DOI":"10.1145\/361219.361220"},{"key":"S1793351X26430014BIB009","doi-asserted-by":"publisher","DOI":"10.1147\/rd.22.0159"},{"key":"S1793351X26430014BIB010","first-page":"22","volume":"11","author":"Lovins J. B.","year":"1968","journal-title":"Mech. Transl. Comput. Linguist."},{"key":"S1793351X26430014BIB011","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9"},{"key":"S1793351X26430014BIB012","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-7552(98)00110-X"},{"key":"S1793351X26430014BIB013","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican0501-34"},{"key":"S1793351X26430014BIB014","unstructured":"E. Prud\u2019hommeaux and A. Seaborne, SPARQL query language for RDF, World Wide Web Consortium (W3C), W3C Recommendation (2008), https:\/\/www.w3.org\/TR\/ 2008\/REC-rdf-sparql-query-20080115\/."},{"key":"S1793351X26430014BIB015","unstructured":"T. Mikolov, K. Chen, G. Corrado and J. Dean, Efficient estimation of word representations in vector space, preprint (2013), arXiv:1301.3781."},{"key":"S1793351X26430014BIB016","first-page":"4171","volume-title":"Proc. 2019 Conf. North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 Long and Short Papers","author":"Devlin J.","year":"2019"},{"key":"S1793351X26430014BIB017","first-page":"333","volume":"3","author":"Robertson S.","year":"2009","journal-title":"Found. Trends Inf. Retr."},{"key":"S1793351X26430014BIB018","author":"Lewis P.","year":"2020","journal-title":"CoRR"},{"key":"S1793351X26430014BIB019","doi-asserted-by":"publisher","DOI":"10.1145\/3673791.3698426"},{"key":"S1793351X26430014BIB020","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-020-00212-w"},{"key":"S1793351X26430014BIB021","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3508471"},{"key":"S1793351X26430014BIB022","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2026.104993"},{"key":"S1793351X26430014BIB023","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2025.1622292"},{"key":"S1793351X26430014BIB024","doi-asserted-by":"publisher","DOI":"10.1007\/s42524-025-4213-0"},{"key":"S1793351X26430014BIB025","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC60802.2025.11423539"},{"key":"S1793351X26430014BIB026","unstructured":"C. Chen, Y. He, H. Wang, J. Chen and Q. Luo, DelayPTC-LLM: Metro passenger travel choice prediction under train delays with large language models, preprint (2024), arXiv:2410.00052."},{"key":"S1793351X26430014BIB027","doi-asserted-by":"publisher","DOI":"10.1016\/j.tra.2025.104542"},{"key":"S1793351X26430014BIB028","doi-asserted-by":"publisher","DOI":"10.1109\/VNC61989.2024.10575993"},{"key":"S1793351X26430014BIB029","unstructured":"T. Zhe, R. Liu, F. Memar, X. Luo, W. Fan, X. Ye, Z. Peng and D. Wang, Constraint-aware route recommendation from natural language via hierarchical LLM agents, preprint (2025), arXiv:2510.06078."},{"key":"S1793351X26430014BIB030","doi-asserted-by":"publisher","DOI":"10.3390\/math13050856"},{"key":"S1793351X26430014BIB031","doi-asserted-by":"publisher","DOI":"10.2196\/70176"},{"key":"S1793351X26430014BIB032","doi-asserted-by":"publisher","DOI":"10.1109\/AIxB62249.2024.00021"},{"key":"S1793351X26430014BIB033","doi-asserted-by":"publisher","DOI":"10.1109\/RoboticCC68732.2025.00016"},{"key":"S1793351X26430014BIB034","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA251450"},{"key":"S1793351X26430014BIB035","doi-asserted-by":"publisher","DOI":"10.1111\/gean.70009"},{"key":"S1793351X26430014BIB036","unstructured":"Tavily, Tavily search API documentation (2025), https:\/\/docs.tavily.com."},{"key":"S1793351X26430014BIB037","unstructured":"Ollama, Llama 3.2, Version 3.2 (2025), https:\/\/ollama.com\/library\/llama3.2."},{"key":"S1793351X26430014BIB038","doi-asserted-by":"publisher","DOI":"10.1145\/3615359"},{"key":"S1793351X26430014BIB039","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300233"},{"key":"S1793351X26430014BIB040","volume-title":"The Design of Everyday Things","author":"Norman D. A.","year":"2013"},{"key":"S1793351X26430014BIB041","unstructured":"Z. Jiang\n                      et al.\n                      , Prompting GPT-3 to be reliable, preprint (2023), arXiv:2210.09150."},{"key":"S1793351X26430014BIB042","first-page":"1","volume-title":"Proc. 2023 CHI Conf. Human Factors in Computing Systems","author":"Zamfirescu-Pereira J.","year":"2023"},{"key":"S1793351X26430014BIB043","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2020.1741118"},{"key":"S1793351X26430014BIB044","doi-asserted-by":"publisher","DOI":"10.1037\/xge0000033"},{"key":"S1793351X26430014BIB045","doi-asserted-by":"publisher","DOI":"10.1007\/s10732-014-9242-5"},{"key":"S1793351X26430014BIB046","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2010.03.045"},{"key":"S1793351X26430014BIB047","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"S1793351X26430014BIB048","first-page":"9459","volume":"33","author":"Lewis P.","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S1793351X26430014BIB049","doi-asserted-by":"crossref","unstructured":"S. Valmeekam, M. Marquez, S. Sreedharan and S. Kambhampati, On the planning abilities of large language models: A critical investigation, preprint (2023), arXiv:2305.15771.","DOI":"10.52202\/075280-3320"},{"issue":"8","key":"S1793351X26430014BIB050","first-page":"1550","volume":"34","author":"Mai G.","year":"2020","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"S1793351X26430014BIB051","doi-asserted-by":"publisher","DOI":"10.1080\/13658816.2019.1684500"},{"key":"S1793351X26430014BIB052","first-page":"3929","volume-title":"Proc. 37th Int. Conf. Machine Learning","volume":"119","author":"Guu K.","year":"2020"},{"key":"S1793351X26430014BIB053","volume-title":"The Traveling Salesman Problem: A Computational Study","author":"Applegate D. L.","year":"2006"},{"key":"S1793351X26430014BIB054","volume-title":"Combinatorial Optimization: Algorithms and Complexity","author":"Papadimitriou C. H.","year":"1998"},{"key":"S1793351X26430014BIB055","unstructured":"X. Chen\n                      et al.\n                      , Evaluating large language models for mathematical reasoning, preprint (2023), arXiv:2303.08943."},{"key":"S1793351X26430014BIB056","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2997"},{"key":"S1793351X26430014BIB057","volume-title":"Int. Conf. Learning Representations","author":"Yao S.","year":"2023"}],"container-title":["International Journal of Semantic Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S1793351X26430014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T07:11:04Z","timestamp":1787209864000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S1793351X26430014"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,30]]},"references-count":57,"journal-issue":{"issue":"03","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["10.1142\/S1793351X26430014"],"URL":"https:\/\/doi.org\/10.1142\/s1793351x26430014","relation":{},"ISSN":["1793-351X","1793-7108"],"issn-type":[{"value":"1793-351X","type":"print"},{"value":"1793-7108","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,30]]}}}