{"id":"https://openalex.org/W7161696346","doi":"https://doi.org/10.48550/arxiv.2605.17137","title":"Latent Heuristic Search: Continuous Optimization for Automated Algorithm Design","display_name":"Latent Heuristic Search: Continuous Optimization for Automated Algorithm Design","publication_year":2026,"publication_date":"2026-05-16","ids":{"openalex":"https://openalex.org/W7161696346","doi":"https://doi.org/10.48550/arxiv.2605.17137"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.17137","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17137","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.17137","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136485677","display_name":"Cheikh Ahmed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmed, Cheikh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042614566","display_name":"Mahdi Mostajabdaveh","orcid":"https://orcid.org/0000-0002-2816-909X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mostajabdaveh, Mahdi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136502731","display_name":"Zirui Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Zirui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.21160000562667847,"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"}},"topics":[{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.21160000562667847,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0658000037074089,"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/T12176","display_name":"Optimization and Packing Problems","score":0.05990000069141388,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/continuous-optimization","display_name":"Continuous optimization","score":0.632099986076355},{"id":"https://openalex.org/keywords/discrete-optimization","display_name":"Discrete optimization","score":0.539900004863739},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5098999738693237},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.47510001063346863},{"id":"https://openalex.org/keywords/knapsack-problem","display_name":"Knapsack problem","score":0.4537999927997589},{"id":"https://openalex.org/keywords/metaheuristic","display_name":"Metaheuristic","score":0.3540000021457672},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"Stochastic optimization","score":0.3402999937534332},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.33880001306533813},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.3312999904155731}],"concepts":[{"id":"https://openalex.org/C92995354","wikidata":"https://www.wikidata.org/wiki/Q5165499","display_name":"Continuous optimization","level":4,"score":0.632099986076355},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6308000087738037},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.57669997215271},{"id":"https://openalex.org/C145671259","wikidata":"https://www.wikidata.org/wiki/Q1493786","display_name":"Discrete optimization","level":3,"score":0.539900004863739},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5098999738693237},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C113138325","wikidata":"https://www.wikidata.org/wiki/Q864457","display_name":"Knapsack problem","level":2,"score":0.4537999927997589},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4397999942302704},{"id":"https://openalex.org/C109718341","wikidata":"https://www.wikidata.org/wiki/Q1385229","display_name":"Metaheuristic","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.3402999937534332},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C188919014","wikidata":"https://www.wikidata.org/wiki/Q5422296","display_name":"Extremal optimization","level":4,"score":0.3027999997138977},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2904999852180481},{"id":"https://openalex.org/C164752517","wikidata":"https://www.wikidata.org/wiki/Q5570875","display_name":"Global optimization","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2782999873161316},{"id":"https://openalex.org/C153782549","wikidata":"https://www.wikidata.org/wiki/Q175116","display_name":"Discrete space","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C135320971","wikidata":"https://www.wikidata.org/wiki/Q1868524","display_name":"Local search (optimization)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C175859090","wikidata":"https://www.wikidata.org/wiki/Q322212","display_name":"Travelling salesman problem","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.17137","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17137","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.17137","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.17137","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,105,180],"integration":[1],"of":[2,30],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"into":[7,68,116],"evolutionary":[8,168],"frameworks":[9],"has":[10],"established":[11],"a":[12,39,47,56,73,96,113,121,172],"new":[13],"paradigm":[14],"for":[15,176],"automated":[16,177],"heuristic":[17,49],"discovery.":[18],"Despite":[19],"their":[20],"promise,":[21],"these":[22,93],"methods":[23],"typically":[24],"search":[25],"in":[26],"the":[27,85,131,135,140,146],"discrete":[28,66,167],"space":[29],"program":[31],"syntax,":[32],"relying":[33],"on":[34,134],"stochastic":[35],"sampling":[36],"to":[37,55,64,77,95,124],"navigate":[38],"highly":[40],"non-convex":[41],"optimization":[42,54,86,161],"landscape.":[43],"This":[44],"work":[45],"proposes":[46],"continuous":[48,69,159],"discovery":[50],"framework":[51],"that":[52,158],"shifts":[53],"learned":[57,114],"latent":[58,108],"manifold.":[59],"We":[60,129],"employ":[61],"an":[62,88],"encoder":[63],"map":[65],"programs":[67],"embeddings":[70,94],"and":[71,150],"train":[72],"differentiable":[74],"surrogate":[75],"model":[76],"predict":[78],"performance,":[79],"enabling":[80],"gradient-based":[81],"search.":[82],"To":[83],"regularize":[84],"trajectory,":[87],"invertible":[89],"normalizing":[90],"flow":[91],"maps":[92],"structured":[97],"Gaussian":[98],"prior,":[99],"where":[100],"we":[101],"perform":[102],"gradient":[103],"ascent.":[104],"resulting":[106],"optimized":[107],"vectors":[109],"are":[110],"projected":[111],"through":[112],"mapper":[115],"soft":[117],"prompts,":[118],"which":[119],"condition":[120],"frozen":[122],"LLM":[123],"synthesize":[125],"novel":[126],"executable":[127],"heuristics.":[128],"evaluate":[130],"proposed":[132],"method":[133],"Traveling":[136],"Salesman":[137],"Problem":[138,144,148],"(TSP),":[139],"Capacitated":[141],"Vehicle":[142],"Routing":[143],"(CVRP),":[145],"Knapsack":[147],"(KSP),":[149],"Online":[151],"Bin":[152],"Packing":[153],"(OBP).":[154],"Empirical":[155],"results":[156],"demonstrate":[157],"latent-space":[160],"achieves":[162],"performance":[163],"competitive":[164],"with":[165],"state-of-the-art":[166],"baselines":[169],"while":[170],"offering":[171],"complementary":[173],"methodological":[174],"alternative":[175],"algorithm":[178],"design.":[179],"implementation":[181],"code":[182],"is":[183],"available":[184],"at":[185],"\\url{https://github.com/cheikh025/LHS}.":[186]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-20T00:00:00"}