{"id":"https://openalex.org/W6948053835","doi":"https://doi.org/10.48550/arxiv.2505.08735","title":"Preference Optimization for Combinatorial Optimization Problems","display_name":"Preference Optimization for Combinatorial Optimization Problems","publication_year":2025,"publication_date":"2025-05-13","ids":{"openalex":"https://openalex.org/W6948053835","doi":"https://doi.org/10.48550/arxiv.2505.08735"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.08735","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.08735","pdf_url":"https://arxiv.org/pdf/2505.08735","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.08735","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Pan, Mingjun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Mingjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lin, Guanquan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Guanquan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Luo, You-Wei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, You-Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhu, Bin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Bin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Dai, Zhien","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Zhien","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Sun, Lijun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Lijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Yuan, Chun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Chun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.334199994802475,"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"}},"topics":[{"id":"https://openalex.org/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.334199994802475,"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"}},{"id":"https://openalex.org/T10567","display_name":"Vehicle Routing Optimization Methods","score":0.3061999976634979,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.26269999146461487,"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/preference-optimization","display_name":"preference optimization","score":0.7559999823570251},{"id":"https://openalex.org/keywords/neural-combinatorial-optimization","display_name":"neural combinatorial optimization","score":0.8169999718666077},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7110000252723694},{"id":"https://openalex.org/keywords/preference-models","display_name":"preference models","score":0.5249999761581421},{"id":"https://openalex.org/keywords/entropy-regularization","display_name":"entropy regularization","score":0.8299999833106995},{"id":"https://openalex.org/keywords/local-search","display_name":"local search","score":0.8420000076293945},{"id":"https://openalex.org/keywords/traveling-salesman-problem","display_name":"traveling salesman problem","score":0.7160000205039978},{"id":"https://openalex.org/keywords/capacitated-vehicle-routing-problem","display_name":"capacitated vehicle routing problem","score":0.9909999966621399},{"id":"https://openalex.org/keywords/hybrid-flow-shop-scheduling","display_name":"hybrid flow shop scheduling","score":0.8690000176429749}],"concepts":[{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6565999984741211},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6248000264167786},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6028000116348267},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.593500018119812},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5738000273704529},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.5105999708175659},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.4925000071525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46970000863075256},{"id":"https://openalex.org/C52692508","wikidata":"https://www.wikidata.org/wiki/Q1333872","display_name":"Combinatorial optimization","level":2,"score":0.4641999900341034},{"id":"https://openalex.org/C175859090","wikidata":"https://www.wikidata.org/wiki/Q322212","display_name":"Travelling salesman problem","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C123784306","wikidata":"https://www.wikidata.org/wiki/Q944041","display_name":"Vehicle routing problem","level":3,"score":0.4242999851703644},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3653999865055084},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C135320971","wikidata":"https://www.wikidata.org/wiki/Q1868524","display_name":"Local search (optimization)","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C2781043087","wikidata":"https://www.wikidata.org/wiki/Q939761","display_name":"Preference theory","level":3,"score":0.3086000084877014},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2606000006198883},{"id":"https://openalex.org/C106472803","wikidata":"https://www.wikidata.org/wiki/Q291440","display_name":"2-opt","level":3,"score":0.2556999921798706},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2433999925851822},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.21879999339580536},{"id":"https://openalex.org/C109718341","wikidata":"https://www.wikidata.org/wiki/Q1385229","display_name":"Metaheuristic","level":2,"score":0.21819999814033508},{"id":"https://openalex.org/C126661757","wikidata":"https://www.wikidata.org/wiki/Q4925641","display_name":"Random search","level":2,"score":0.21780000627040863},{"id":"https://openalex.org/C188919014","wikidata":"https://www.wikidata.org/wiki/Q5422296","display_name":"Extremal optimization","level":4,"score":0.21770000457763672},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.21739999949932098},{"id":"https://openalex.org/C115908005","wikidata":"https://www.wikidata.org/wiki/Q2668364","display_name":"Combinatorial explosion","level":2,"score":0.2079000025987625},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.20739999413490295},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2070000022649765},{"id":"https://openalex.org/C201789804","wikidata":"https://www.wikidata.org/wiki/Q2362762","display_name":"Search problem","level":2,"score":0.20389999449253082},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.20239999890327454},{"id":"https://openalex.org/C75782508","wikidata":"https://www.wikidata.org/wiki/Q3333633","display_name":"Cross-entropy method","level":4,"score":0.19359999895095825},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.19349999725818634},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.19329999387264252},{"id":"https://openalex.org/C203208320","wikidata":"https://www.wikidata.org/wiki/Q5150830","display_name":"Combinatorial search","level":4,"score":0.19009999930858612},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.18950000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.08735","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.08735","pdf_url":"https://arxiv.org/pdf/2505.08735","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.08735","doi":"https://doi.org/10.48550/arxiv.2505.08735","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.08735","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.08735","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.08735","pdf_url":"https://arxiv.org/pdf/2505.08735","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337253","display_name":"Instituto de Ciencias del Mar y Limnolog\u00eda, Universidad Nacional Aut\u00f3noma de M\u00e9xico","ror":"https://ror.org/040wdye98"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6948053835.pdf","grobid_xml":"https://content.openalex.org/works/W6948053835.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2560592986","https://openalex.org/W3116111955","https://openalex.org/W4379473794","https://openalex.org/W4382237551","https://openalex.org/W4393312686","https://openalex.org/W4401025096","https://openalex.org/W4402670301","https://openalex.org/W4404782689","https://openalex.org/W4415795501","https://openalex.org/W7133183399"],"related_works":["https://openalex.org/W7223273341","https://openalex.org/W3009304813","https://openalex.org/W4417148804","https://openalex.org/W1944560301","https://openalex.org/W3081235889","https://openalex.org/W3097232108","https://openalex.org/W4293434055","https://openalex.org/W90296522","https://openalex.org/W2560592986","https://openalex.org/W4399026279"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"has":[3],"emerged":[4],"as":[5,35,139],"a":[6,57],"powerful":[7],"tool":[8],"for":[9],"neural":[10],"combinatorial":[11,44],"optimization,":[12],"enabling":[13],"models":[14],"to":[15,48,122],"learn":[16],"heuristics":[17],"that":[18,60,99,159],"solve":[19],"complex":[20],"problems":[21],"without":[22],"requiring":[23],"expert":[24],"knowledge.":[25],"Despite":[26],"significant":[27],"progress,":[28],"existing":[29,164],"RL":[30,97,165],"approaches":[31],"face":[32],"challenges":[33],"such":[34,138],"diminishing":[36],"reward":[37,63,83],"signals":[38,64,68],"and":[39,89,151,171],"inefficient":[40],"exploration":[41],"in":[42,85],"vast":[43],"action":[45],"spaces,":[46],"leading":[47],"inefficiency.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,93,111],"propose":[54],"Preference":[55],"Optimization,":[56],"novel":[58],"method":[59,161],"transforms":[61],"quantitative":[62],"into":[65,116],"qualitative":[66],"preference":[67,91,125],"via":[69],"statistical":[70],"comparison":[71],"modeling,":[72],"emphasizing":[73],"the":[74,82,101,117,128,140,145,152],"superiority":[75],"among":[76],"sampled":[77],"solutions.":[78],"Methodologically,":[79],"by":[80],"reparameterizing":[81],"function":[84],"terms":[86],"of":[87],"policy":[88,102,129],"utilizing":[90],"models,":[92],"formulate":[94],"an":[95],"entropy-regularized":[96],"objective":[98],"aligns":[100],"directly":[103],"with":[104],"preferences":[105],"while":[106],"avoiding":[107],"intractable":[108],"computations.":[109],"Furthermore,":[110],"integrate":[112],"local":[113,131],"search":[114],"techniques":[115],"fine-tuning":[118],"rather":[119],"than":[120],"post-processing":[121],"generate":[123],"high-quality":[124],"pairs,":[126],"helping":[127],"escape":[130],"optima.":[132],"Empirical":[133],"results":[134],"on":[135],"various":[136],"benchmarks,":[137],"Traveling":[141],"Salesman":[142],"Problem":[143,149,156],"(TSP),":[144],"Capacitated":[146],"Vehicle":[147],"Routing":[148],"(CVRP)":[150],"Flexible":[153],"Flow":[154],"Shop":[155],"(FFSP),":[157],"demonstrate":[158],"our":[160],"significantly":[162],"outperforms":[163],"algorithms,":[166],"achieving":[167],"superior":[168],"convergence":[169],"efficiency":[170],"solution":[172],"quality.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}