{"id":"https://openalex.org/W7114912747","doi":"https://doi.org/10.1145/3748636.3764603","title":"Learning Heuristics to Solve Dynamic Vehicle Routing Problems Using Large Language Models","display_name":"Learning Heuristics to Solve Dynamic Vehicle Routing Problems Using Large Language Models","publication_year":2025,"publication_date":"2025-11-03","ids":{"openalex":"https://openalex.org/W7114912747","doi":"https://doi.org/10.1145/3748636.3764603"},"language":"en","primary_location":{"id":"doi:10.1145/3748636.3764603","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748636.3764603","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3748636.3764603","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Advances in Geographic Information Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3748636.3764603","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Andrew Wang","orcid":"https://orcid.org/0009-0002-2781-8219"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Andrew Wang","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":"https://orcid.org/0009-0002-2781-8219","affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoyan Li","orcid":"https://orcid.org/0000-0002-0215-819X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xiaoyan Li","raw_affiliation_strings":["University of Toronto, Toronto, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-0215-819X","affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, ON, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yunli Wang","orcid":"https://orcid.org/0000-0002-2320-954X"},"institutions":[{"id":"https://openalex.org/I4210159778","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06","country_code":"CA","type":"government","lineage":["https://openalex.org/I4210159778"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yunli Wang","raw_affiliation_strings":["National Research Council Canada, Ottawa, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0002-2320-954X","affiliations":[{"raw_affiliation_string":"National Research Council Canada, Ottawa, ON, Canada","institution_ids":["https://openalex.org/I4210159778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"729","last_page":"738"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10567","display_name":"Vehicle Routing Optimization Methods","score":0.9599999785423279,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10567","display_name":"Vehicle Routing Optimization Methods","score":0.9599999785423279,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.00559999980032444,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.0024999999441206455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7861999869346619},{"id":"https://openalex.org/keywords/vehicle-routing-problem","display_name":"Vehicle routing problem","score":0.6714000105857849},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6520000100135803},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5566999912261963},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.5358999967575073},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.5105000138282776},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5006999969482422},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.4943000078201294}],"concepts":[{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7861999869346619},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7509999871253967},{"id":"https://openalex.org/C123784306","wikidata":"https://www.wikidata.org/wiki/Q944041","display_name":"Vehicle routing problem","level":3,"score":0.6714000105857849},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6520000100135803},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5566999912261963},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.5358999967575073},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.5105000138282776},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.4943000078201294},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4090000092983246},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40869998931884766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4065000116825104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38760000467300415},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2863999903202057},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.28600001335144043},{"id":"https://openalex.org/C117270229","wikidata":"https://www.wikidata.org/wiki/Q5957539","display_name":"Hyper-heuristic","level":5,"score":0.27720001339912415},{"id":"https://openalex.org/C2778536092","wikidata":"https://www.wikidata.org/wiki/Q4785038","display_name":"Arc routing","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3748636.3764603","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748636.3764603","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3748636.3764603","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Advances in Geographic Information Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:0f6c3da8-ed6c-497a-be08-5fabf1b6dc59","is_oa":true,"landing_page_url":"https://nrc-publications.canada.ca/eng/view/object/?id=0f6c3da8-ed6c-497a-be08-5fabf1b6dc59","pdf_url":"https://nrc-publications.canada.ca/eng/view/ft/?id=0f6c3da8-ed6c-497a-be08-5fabf1b6dc59","source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1145/3748636.3764603","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3748636.3764603","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3748636.3764603","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Advances in Geographic Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5298337936401367,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G101874668","display_name":null,"funder_award_id":"Ai4L 133","funder_id":"https://openalex.org/F4320334601","funder_display_name":"National Research Council Canada"}],"funders":[{"id":"https://openalex.org/F4320334601","display_name":"National Research Council Canada","ror":"https://ror.org/04mte1k06"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7114912747.pdf","grobid_xml":"https://content.openalex.org/works/W7114912747.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2112094258","https://openalex.org/W2597664555","https://openalex.org/W2797064164","https://openalex.org/W3037428092","https://openalex.org/W3047863327","https://openalex.org/W3109386843","https://openalex.org/W3187269752"],"related_works":[],"abstract_inverted_index":{"Modern":[0],"logistics":[1],"companies":[2],"face":[3],"significant":[4,190],"challenges":[5],"in":[6,13,157],"efficiently":[7],"managing":[8],"dynamic":[9],"transportation":[10],"systems,":[11],"particularly":[12],"addressing":[14],"Dynamic":[15],"Vehicle":[16,129],"Routing":[17,130],"Problems":[18,131],"(DVRP).":[19],"These":[20],"complex":[21],"problems":[22],"require":[23],"specialized":[24],"expertise":[25],"for":[26,38,51,89,109,192],"effective":[27,149],"algorithm":[28,36],"design.":[29],"Traditional":[30],"approaches":[31,174],"often":[32],"rely":[33],"on":[34,119],"manual":[35],"design":[37],"specific":[39],"routing":[40,53,127],"problems.":[41],"Reinforcement":[42],"learning":[43,49,87],"(RL)-based":[44],"methods,":[45],"though":[46],"capable":[47],"of":[48,77,177],"heuristics":[50,94,150],"diverse":[52],"problems,":[54],"suffer":[55],"from":[56],"poor":[57],"training":[58,114],"efficiency":[59],"and":[60,82,95,139,151,162,173,186],"weak":[61],"generalization":[62,75],"to":[63],"out-of-distribution":[64],"(OOD)":[65],"scenarios.":[66],"To":[67],"address":[68],"these":[69],"limitations,":[70],"we":[71],"leverage":[72],"the":[73,175],"strong":[74],"capabilities":[76],"large":[78],"language":[79],"models":[80],"(LLMs)":[81],"adopt":[83],"an":[84,101],"LLM-based":[85],"heuristic":[86],"approach":[88,147],"DVRP.":[90],"Our":[91],"method":[92,165,182],"learns":[93,148],"autonomously":[96],"generates":[97],"executable":[98],"code":[99],"within":[100],"evolutionary":[102],"framework,":[103],"requiring":[104],"fewer":[105],"than":[106,170],"10":[107],"samples":[108],"training.":[110],"This":[111],"enables":[112],"fast":[113],"while":[115],"maintaining":[116],"robust":[117],"performance":[118,176],"large-scale":[120],"OOD":[121],"instances.":[122],"Comprehensive":[123],"experiments":[124],"across":[125],"multiple":[126],"problems\u2014including":[128],"(VRP),":[132],"VRP":[133],"with":[134,141,189],"Time":[135,142],"Windows":[136,143],"(VRPTW),":[137],"DVRP,":[138],"DVRP":[140],"(DVRPTW)\u2014demonstrate":[144],"that":[145],"our":[146,164],"consistently":[152],"surpasses":[153],"Greedy":[154,171],"baselines.":[155],"Moreover,":[156],"constrained":[158],"optimization":[159],"tasks":[160],"(VRPTW":[161],"DVRPTW),":[163],"attains":[166],"higher":[167],"feasibility":[168],"rates":[169],"baselines":[172],"expert-designed":[178],"heuristics.":[179],"The":[180],"proposed":[181],"presents":[183],"a":[184],"promising":[185],"scalable":[187],"solution":[188],"potential":[191],"real-world":[193],"industrial":[194],"deployment.1":[195]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-12T00:00:00"}