{"id":"https://openalex.org/W7161293613","doi":"https://doi.org/10.48550/arxiv.2605.14141","title":"Distribution-Aware Algorithm Design with LLM Agents","display_name":"Distribution-Aware Algorithm Design with LLM Agents","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7161293613","doi":"https://doi.org/10.48550/arxiv.2605.14141"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.14141","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14141","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,"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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.14141","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136222902","display_name":"Saharsh Koganti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koganti, Saharsh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109708236","display_name":"P. Mishra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mishra, Priyadarsi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136238918","display_name":"Pierfrancesco Beneventano","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Beneventano, Pierfrancesco","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050776111","display_name":"Tomer Galanti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Galanti, Tomer","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/T12535","display_name":"Machine Learning and Data Classification","score":0.37459999322891235,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.37459999322891235,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.1256999969482422,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.057100001722574234,"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/solver","display_name":"Solver","score":0.8342000246047974},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.8140000104904175},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7167999744415283},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5245000123977661},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5138999819755554},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4803999960422516},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4537999927997589},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.430400013923645},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.3953000009059906}],"concepts":[{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.8342000246047974},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.8140000104904175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7556999921798706},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7167999744415283},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5245000123977661},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5138999819755554},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48260000348091125},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4803999960422516},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4537999927997589},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.430400013923645},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.396699994802475},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3790999948978424},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C111696304","wikidata":"https://www.wikidata.org/wiki/Q2303697","display_name":"Sorting","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C108094655","wikidata":"https://www.wikidata.org/wiki/Q181593","display_name":"Sorting algorithm","level":3,"score":0.29649999737739563},{"id":"https://openalex.org/C6943359","wikidata":"https://www.wikidata.org/wiki/Q875276","display_name":"Boolean satisfiability problem","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27720001339912415},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.2590999901294708},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.25519999861717224},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.14141","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14141","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.14141","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14141","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,"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":"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":{"Many":[0],"optimization":[1],"problems":[2],"arise":[3],"repeatedly":[4],"from":[5,39,68,101],"a":[6,62,74,167,232],"fixed":[7,91],"but":[8],"unknown":[9],"distribution.":[10],"Even":[11],"when":[12],"the":[13,79,107,190,193,206,213],"worst-case":[14],"problem":[15,119],"is":[16,61,216],"hard,":[17],"this":[18],"distribution":[19],"may":[20],"carry":[21],"reusable":[22],"structure,":[23],"such":[24,37],"as":[25],"recurring":[26],"geometry,":[27],"decompositions,":[28],"or":[29],"resource":[30],"patterns.":[31],"We":[32,76,105],"study":[33],"how":[34],"to":[35,72],"infer":[36],"structure":[38,66],"sample":[40],"instances":[41,53],"and":[42,70,88,94,139,166,177,184,222,249],"compile":[43,250],"it":[44],"into":[45,252],"solver":[46,83,92,215,254],"code":[47,111],"that":[48,78,95],"runs":[49,223],"faster":[50,134,159,226],"on":[51,113,150,218],"future":[52],"while":[54,129,179],"preserving":[55],"solution":[56,237],"quality.":[57],"Our":[58],"central":[59],"abstraction":[60],"\\emph{solver":[63],"hint}:":[64],"distribution-specific":[65,246],"inferred":[67],"samples":[69],"used":[71],"specialize":[73],"solver.":[75],"prove":[77],"empirically":[80],"fastest":[81],"sample-consistent":[82],"generalizes":[84],"in":[85],"both":[86],"correctness":[87],"runtime":[89],"over":[90,174,201],"libraries,":[93],"identifiable":[96],"hints":[97],"can":[98,244],"be":[99],"recovered":[100],"polynomially":[102],"many":[103],"samples.":[104],"instantiate":[106],"framework":[108],"with":[109],"LLM":[110,154,203,242],"agents":[112,243],"$21$":[114],"combinatorial-optimization":[115],"distributions":[116],"across":[117],"$7$":[118],"classes.":[120],"The":[121],"synthesized":[122,214],"solvers":[123],"reach":[124],"mean":[125],"normalized":[126],"quality":[127,173,183],"$0.971$":[128],"running":[130,185],"orders":[131],"of":[132,192,235],"magnitude":[133],"than":[135,160,227],"classical":[136],"heuristics,":[137],"Gurobi,":[138],"time-limited":[140],"exact":[141],"backends,":[142],"though":[143],"they":[144,157,171],"do":[145],"not":[146],"dominate":[147],"every":[148,151,202],"baseline":[149],"family.":[152],"Against":[153],"synthesis":[155,195],"baselines,":[156],"are":[158],"one-shot":[161,163],"Codex,":[162],"Claude":[164,175],"Code,":[165],"best-of-$5$":[168],"open-model":[169],"variant;":[170],"improve":[172],"Code":[176],"best-of-$5$,":[178],"nearly":[180],"matching":[181],"Codex":[182],"substantially":[186],"faster.":[187],"This":[188],"isolates":[189],"contribution":[191],"iterative":[194],"loop":[196],"without":[197],"claiming":[198],"uniform":[199],"domination":[200],"baseline.":[204],"On":[205],"PACE":[207],"2025":[208],"Dominating":[209],"Set":[210],"private":[211],"instances,":[212],"valid":[217],"all":[219],"$100$":[220],"graphs":[221],"roughly":[224],"$75\\times$--$125\\times$":[225],"released":[228],"competition":[229],"solvers,":[230],"within":[231],"few":[233],"percent":[234],"their":[236],"size.":[238],"These":[239],"results":[240],"suggest":[241],"discover":[245],"computational":[247],"shortcuts":[248],"them":[251],"efficient":[253],"code.":[255]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-16T00:00:00"}