{"id":"https://openalex.org/W7204886048","doi":"https://doi.org/10.18653/2026.findings-emnlp.130","title":"MineCEraft: Evaluating Language Models as Construction Engineers in the World of Minecraft","display_name":"MineCEraft: Evaluating Language Models as Construction Engineers in the World of Minecraft","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204886048","doi":"https://doi.org/10.18653/2026.findings-emnlp.130"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.130","doi":"https://doi.org/10.18653/2026.findings-emnlp.130","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.130","pdf_url":"https://aclanthology.org/2026.findings-emnlp.130.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.findings-emnlp.130.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110776293","display_name":"Sewoong Lee","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sewoong Lee","raw_affiliation_strings":["Siebel School of Computing and Data Science The Grainger College of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siebel School of Computing and Data Science The Grainger College of Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034389677","display_name":"Risham Sidhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Risham Sidhu","raw_affiliation_strings":["Siebel School of Computing and Data Science The Grainger College of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siebel School of Computing and Data Science The Grainger College of Engineering","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042661827","display_name":"Julia Hockenmaier","orcid":"https://orcid.org/0000-0003-2796-1752","observed_orcids":["https://orcid.org/0000-0003-2796-1752"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julia Hockenmaier","raw_affiliation_strings":["Siebel School of Computing and Data Science The Grainger College of Engineering","University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siebel School of Computing and Data Science The Grainger College of Engineering","institution_ids":[]},{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064893585","display_name":"Yoonhwa Jung","orcid":"https://orcid.org/0000-0002-6926-4077","observed_orcids":["https://orcid.org/0000-0002-6926-4077"]},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yoonhwa Jung","raw_affiliation_strings":["Department of Civil and Coastal Engineering University of Florida"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Civil and Coastal Engineering University of Florida","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69544265,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2643","last_page":"2667"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.33980000019073486,"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/T10028","display_name":"Topic Modeling","score":0.33980000019073486,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.16539999842643738,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1525000035762787,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/large-language-models","display_name":"large language models","score":0.7990000247955322},{"id":"https://openalex.org/keywords/construction-engineering","display_name":"construction engineering","score":0.7730000019073486},{"id":"https://openalex.org/keywords/minecraft","display_name":"Minecraft","score":0.9959999918937683},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.8289999961853027},{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.7070000171661377},{"id":"https://openalex.org/keywords/error-analysis","display_name":"error analysis","score":0.7089999914169312},{"id":"https://openalex.org/keywords/failure-modes","display_name":"failure modes","score":0.8330000042915344},{"id":"https://openalex.org/keywords/natural-language-instructions","display_name":"natural language instructions","score":0.847000002861023},{"id":"https://openalex.org/keywords/open-source-benchmark","display_name":"open-source benchmark","score":0.5830000042915344}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7700999975204468},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6736999750137329},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.61080002784729},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6064000129699707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45680001378059387},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.43630000948905945},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.4359999895095825},{"id":"https://openalex.org/C110354214","wikidata":"https://www.wikidata.org/wiki/Q6314146","display_name":"Engineering management","level":1,"score":0.35420000553131104},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3269999921321869},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.32249999046325684},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.30469998717308044},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.28450000286102295},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2500999867916107}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.130","doi":"https://doi.org/10.18653/2026.findings-emnlp.130","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.130","pdf_url":"https://aclanthology.org/2026.findings-emnlp.130.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.28884","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28884","pdf_url":"https://arxiv.org/pdf/2608.28884","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.2608.28884","doi":"https://doi.org/10.48550/arxiv.2608.28884","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.28884","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":"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"}],"best_oa_location":{"id":"doi:10.18653/2026.findings-emnlp.130","doi":"https://doi.org/10.18653/2026.findings-emnlp.130","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.130","pdf_url":"https://aclanthology.org/2026.findings-emnlp.130.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204886048.pdf","grobid_xml":"https://content.openalex.org/works/W7204886048.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415380441","https://openalex.org/W7077459656","https://openalex.org/W4403781291","https://openalex.org/W7161309892","https://openalex.org/W7165900623","https://openalex.org/W4391833829","https://openalex.org/W4415251446","https://openalex.org/W7093306112","https://openalex.org/W4417229368","https://openalex.org/W7106533774"],"abstract_inverted_index":{"We":[0],"introduce":[1],"MineCEraft":[2,29,96],"(Minecraft":[3],"Construction":[4],"Engineering":[5],"Benchmark,":[6],"pronounced":[7],"mine-see-ee-raft),":[8],"an":[9,67],"easy-to-use,":[10],"open-source":[11],"1":[12],"benchmark":[13,30],"designed":[14],"to":[15,57,89,263],"systematically":[16],"evaluate":[17],"the":[18,159,193,197,213,234,261,264,270],"reliability":[19],"and":[20,49,73,83,107,182,196,199,233,252],"limitations":[21],"of":[22,70,162,176,180,186,217],"LLMs":[23,72,88],"for":[24,53,248],"construction":[25,60,90,105,113],"tasks":[26],"in":[27,86,149,189,224,256,288,294],"Minecraft.The":[28],"comprises":[31],"723":[32],"domain-expert":[33],"hand-crafted":[34],"natural-language":[35],"instructions":[36],"with":[37,133,142,173,280],"programmatically":[38],"verifiable":[39],"evaluation,":[40],"spanning":[41],"17":[42],"distinct":[43],"task":[44],"categories,":[45],"providing":[46],"a":[47,75,104,109,112,117,126,143,171,183,218,245,278],"safe":[48],"controllable":[50],"experimental":[51],"environment":[52],"assessing":[54],"LLMs'":[55],"ability":[56],"perform":[58,74],"realistic":[59],"engineering":[61,91],"tasks.With":[62],"this":[63],"benchmark,":[64],"we":[65],"conduct":[66],"in-depth":[68],"evaluation":[69],"state-of-the-art":[71],"detailed":[76],"error":[77],"analysis,":[78],"revealing":[79],"key":[80],"failure":[81],"modes":[82],"practical":[84],"challenges":[85],"applying":[87],"tasks.":[92],"Minecraft":[93],"Agent":[94],"\u2026":[95],"BenchmarkNatural":[97],"Language":[98],"Instruction":[99],"System:":[100],"You":[101],"are":[102,156,205,230],"builder,":[103],"engineer":[106],"also":[108],"worker":[110],"at":[111,192,202,281],"site.\u2026":[114],"User:":[115],"Build":[116,212,244,277],"stone":[118,146],"arch":[119],"bridge.":[120],"A:":[121,208],"Structural":[122,152,209,227],"Element":[123,210,242,275],"-FoundationTask:":[124],"Install":[125],"9\u00d79":[127],"pile":[128],"cap,":[129],"2":[130],"blocks":[131,140,191],"thick,":[132],"six":[134],"1\u00d71":[135],"drilled":[136,154],"piles,":[137],"each":[138],"5":[139],"deep,":[141],"1-block":[144],"span.Use":[145],"blocks.":[147],"Failed":[148,223,255,287],"Shape":[150,225],"&":[151,226],"Stability.The":[153,228],"piles":[155],"built":[157],"above":[158],"ground":[160],"instead":[161],"below":[163],"it.":[164],"B:":[165],"Building":[166],"-Basic":[167],"BuildingTask:":[168],"Let's":[169],"build":[170],"house":[172,247],"pillars":[174],"made":[175,179,185],"stone,":[177],"walls":[178],"dirt,":[181],"roof":[184,291],"green.":[187],"Passed":[188],"Material.Green":[190],"top":[194],"layer,":[195],"corner":[198],"edge":[200],"materials":[201],"walking":[203],"height":[204],"correctly":[206],"placed.":[207],"-FrameTask:":[211],"frame":[214],"(including":[215],"stairs)":[216],"10-story":[219],"building":[220,262,279],"using":[221],"concrete.":[222],"stairs":[229],"not":[231,267],"climbable,":[232],"headroom":[235],"between":[236],"levels":[237],"is":[238,266,292],"insufficient.":[239],"C:":[240,273],"Architectural":[241,274],"-AccessibilityTask:":[243],"wheelchair-accessible":[246],"two":[249],"elderly":[250],"people":[251],"one":[253],"care-giver...":[254],"Shape.The":[257],"path":[258],"from":[259],"inside":[260],"outside":[265],"flat,":[268],"violating":[269],"accessibility":[271],"requirement.":[272],"-CreativityTask:":[276],"least":[282],"three":[283],"different":[284],"ceiling":[285],"heights.":[286],"Physical":[289],"Plausibility.The":[290],"placed":[293],"midair":[295],"without":[296],"support.":[297]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-09-02T00:00:00"}
