{"id":"https://openalex.org/W7165676747","doi":"https://doi.org/10.48550/arxiv.2606.23299","title":"GRIMIP: A General Framework for Instance-Specific Configuration of MIP Solvers Using LLMs","display_name":"GRIMIP: A General Framework for Instance-Specific Configuration of MIP Solvers Using LLMs","publication_year":2026,"publication_date":"2026-06-22","ids":{"openalex":"https://openalex.org/W7165676747","doi":"https://doi.org/10.48550/arxiv.2606.23299"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.23299","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.23299","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.23299","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139216573","display_name":"Yidong Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Yidong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081641600","display_name":"Xuemin Chen","orcid":"https://orcid.org/0000-0003-3820-9195"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xuemin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139127320","display_name":"Chenguang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chenguang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076324570","display_name":"Fangzhou Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Fangzhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139149139","display_name":"Tao Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139194660","display_name":"Tianshu Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Tianshu","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":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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.41760000586509705,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.41760000586509705,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.11020000278949738,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.06679999828338623,"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.593999981880188},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5239999890327454},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.47609999775886536},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.47369998693466187},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4052000045776367},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.3995000123977661},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.3515999913215637},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.34540000557899475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.70169997215271},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.593999981880188},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5239999890327454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49459999799728394},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.47369998693466187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.462799996137619},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.34540000557899475},{"id":"https://openalex.org/C131675550","wikidata":"https://www.wikidata.org/wiki/Q7646884","display_name":"Surrogate model","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3050000071525574},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.295199990272522},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2847999930381775},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.23299","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.23299","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.23299","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.23299","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Configuring":[0],"the":[1,37,67,77,86,96,138,144],"hyperparameters":[2],"of":[3,23,71,80,141,147],"Mixed-integer":[4],"programming":[5],"(MIP)":[6],"solvers":[7],"is":[8],"a":[9,59,91],"high-dimensional,":[10],"instance-dependent":[11],"optimization":[12],"problem":[13,39],"where":[14],"suboptimal":[15],"settings":[16],"can":[17],"degrade":[18],"solving":[19],"time":[20],"by":[21],"orders":[22],"magnitude.":[24],"Default":[25],"configurations":[26],"are":[27],"often":[28],"suboptimal,":[29],"while":[30],"traditional":[31],"tuning":[32],"methods":[33],"either":[34],"suffer":[35],"from":[36],"``cold-start''":[38],"and":[40,102,105,126],"inefficient":[41],"search":[42,79,146],"or":[43],"heavily":[44],"rely":[45],"on":[46,121],"expert":[47],"experience.":[48],"This":[49],"paper":[50],"introduces":[51],"\\textbf{GRIMIP}":[52],"(\\textbf{\\underline{G}}eneral":[53],"\\textbf{\\underline{R}}easoning":[54],"for":[55],"\\textbf{\\underline{I}}nstance-specific":[56],"\\textbf{\\underline{MIP}}":[57],"configuration),":[58],"novel":[60],"hybrid":[61],"intelligence":[62],"framework":[63],"that":[64],"synergistically":[65],"integrates":[66],"semantic":[68],"reasoning":[69,140],"capabilities":[70],"Large":[72],"Language":[73],"Models":[74],"(LLMs)":[75],"with":[76,143],"sample-efficient":[78],"Bayesian":[81],"Optimization":[82],"(BO).":[83],"GRIMIP":[84,113,136],"enables":[85],"LLM":[87],"to":[88],"function":[89],"as":[90],"complete":[92],"probabilistic":[93],"surrogate":[94],"within":[95],"BO":[97,129],"loop,":[98],"significantly":[99],"improving":[100],"performance":[101],"reducing":[103],"sampling":[104],"evaluation":[106],"costs.":[107],"On":[108],"seven":[109],"benchmarks":[110],"including":[111],"MIPLIB,":[112],"achieves":[114],"over":[115],"40\\%":[116],"reduction":[117],"in":[118],"Primal-Dual":[119],"Integral":[120],"hard":[122],"instances,":[123],"outperforming":[124],"SMAC":[125],"other":[127],"LLM-assisted":[128],"methods.":[130],"By":[131],"granting":[132],"LLMs":[133,142],"sufficient":[134],"autonomy,":[135],"combines":[137],"expert-level":[139],"efficient":[145],"BO,":[148],"achieving":[149],"state-of-the-art":[150],"performance.":[151]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-24T00:00:00"}