{"id":"https://openalex.org/W7140216857","doi":"https://doi.org/10.48550/arxiv.2603.20253","title":"SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs","display_name":"SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs","publication_year":2026,"publication_date":"2026-03-11","ids":{"openalex":"https://openalex.org/W7140216857","doi":"https://doi.org/10.48550/arxiv.2603.20253"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.20253","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20253","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.2603.20253","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Cao, Yadi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cao, Yadi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lai, Sicheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lai, Sicheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Huang, Jiahe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jiahe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lawrence, Zach","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lawrence, Zach","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Bhakta, Rohan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhakta, Rohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Thomas, Izzy F.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas, Izzy F.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Cao, Mingyun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Mingyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Tsai, Chung-Hao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsai, Chung-Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhou, Zihao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Zihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhao, Yidong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yidong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Hao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Marinoni, Alessandro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marinoni, Alessandro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Arefiev, Alexey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arefiev, Alexey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Yu, Rose","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Rose","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":15,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.15549999475479126,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.15549999475479126,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11751","display_name":"Lattice Boltzmann Simulation Studies","score":0.0649000033736229,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.058400001376867294,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7961999773979187},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6075000166893005},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5414000153541565},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.3619999885559082},{"id":"https://openalex.org/keywords/frontier","display_name":"Frontier","score":0.3610999882221222},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3343000113964081}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7961999773979187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6118000149726868},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6075000166893005},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5414000153541565},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3343000113964081},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3296999931335449},{"id":"https://openalex.org/C15524039","wikidata":"https://www.wikidata.org/wiki/Q865817","display_name":"Java applet","level":3,"score":0.3158000111579895},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.30550000071525574},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.30079999566078186},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C13736549","wikidata":"https://www.wikidata.org/wiki/Q4489420","display_name":"Industrial engineering","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27489998936653137},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2662999927997589},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.26489999890327454},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.262800008058548}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.20253","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20253","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.2603.20253","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.20253","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":[{"display_name":"Industry, innovation and infrastructure","score":0.461212158203125,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Evaluating":[0],"LLM":[1,52],"agents":[2],"for":[3,119,147,163,185,189],"scientific":[4],"tasks":[5,77],"has":[6],"focused":[7],"on":[8,180],"token":[9],"costs":[10,14],"while":[11],"ignoring":[12],"tool-use":[13],"like":[15,25],"simulation":[16,192],"time":[17],"and":[18,63,71,86,95,151,157,165,174,188,195],"experimental":[19],"resources.":[20],"As":[21],"a":[22,171],"result,":[23],"metrics":[24],"pass@k":[26],"become":[27],"impractical":[28],"under":[29,109],"realistic":[30],"budget":[31],"constraints.":[32],"To":[33],"address":[34],"this":[35],"gap,":[36],"we":[37],"introduce":[38],"SimulCost,":[39],"the":[40,152],"first":[41],"benchmark":[42,173],"targeting":[43],"cost-sensitive":[44,54],"parameter":[45,144],"tuning":[46,53],"in":[47,60,103],"physics":[48,186],"simulations.":[49],"SimulCost":[50,169],"compares":[51],"parameters":[55],"against":[56],"traditional":[57,135],"scanning":[58],"approach":[59],"both":[61],"accuracy":[62,111,121],"computational":[64],"cost,":[65],"spanning":[66],"2,916":[67],"single-round":[68,104],"(initial":[69],"guess)":[70],"1,900":[72],"multi-round":[73],"(adjustment":[74],"by":[75],"trial-and-error)":[76],"across":[78],"12":[79],"simulators":[80],"from":[81],"fluid":[82],"dynamics,":[83],"solid":[84],"mechanics,":[85],"plasma":[87],"physics.":[88],"Each":[89],"simulator's":[90],"cost":[91],"is":[92],"analytically":[93],"defined":[94],"platform-independent.":[96],"Frontier":[97],"LLMs":[98,130],"achieve":[99],"46--64%":[100],"success":[101],"rates":[102,126],"mode,":[105],"dropping":[106],"to":[107,127,177],"35--54%":[108],"high":[110,120],"requirements,":[112],"rendering":[113],"their":[114],"initial":[115],"guesses":[116],"unreliable":[117],"especially":[118],"tasks.":[122],"Multi-round":[123],"mode":[124],"improves":[125],"71--80%,":[128],"but":[129],"are":[131,197],"1.5--2.5x":[132],"slower":[133],"than":[134],"scanning,":[136],"making":[137],"them":[138],"uneconomical":[139],"choices.":[140],"We":[141,167],"also":[142],"investigate":[143],"group":[145],"correlations":[146],"knowledge":[148],"transfer":[149],"potential,":[150],"impact":[153],"of":[154],"in-context":[155],"examples":[156],"reasoning":[158],"effort,":[159],"providing":[160],"practical":[161],"implications":[162],"deployment":[164],"fine-tuning.":[166],"open-source":[168],"as":[170],"static":[172],"extensible":[175],"toolkit":[176],"facilitate":[178],"research":[179],"improving":[181],"cost-aware":[182],"agentic":[183],"designs":[184],"simulations,":[187],"expanding":[190],"new":[191],"environments.":[193],"Code":[194],"data":[196],"available":[198],"at":[199],"https://github.com/Rose-STL-Lab/SimulCost-Bench.":[200]},"counts_by_year":[],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2026-03-25T00:00:00"}
