{"id":"https://openalex.org/W7166829324","doi":"https://doi.org/10.18653/v1/2026.findings-acl.371","title":"SupChain-Bench: Benchmarking Large Language Models for Real-World Supply Chain Management","display_name":"SupChain-Bench: Benchmarking Large Language Models for Real-World Supply Chain Management","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166829324","doi":"https://doi.org/10.18653/v1/2026.findings-acl.371"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.371","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.371","pdf_url":"https://aclanthology.org/2026.findings-acl.371.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.371.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125561829","display_name":"Shengyue Guan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengyue Guan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139764037","display_name":"Yihao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihao Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139728926","display_name":"Lang Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lang Cao","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86928525,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7526","last_page":"7550"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.0689999982714653,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.0689999982714653,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.06310000270605087,"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/T11918","display_name":"Forecasting Techniques and Applications","score":0.0625,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5479999780654907},{"id":"https://openalex.org/keywords/supply-chain","display_name":"Supply chain","score":0.5040000081062317},{"id":"https://openalex.org/keywords/supply-chain-management","display_name":"Supply chain management","score":0.4706999957561493},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.39660000801086426},{"id":"https://openalex.org/keywords/supply-chain-risk-management","display_name":"Supply chain risk management","score":0.3197999894618988},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.27730000019073486}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5479999780654907},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5231000185012817},{"id":"https://openalex.org/C108713360","wikidata":"https://www.wikidata.org/wiki/Q1824206","display_name":"Supply chain","level":2,"score":0.5040000081062317},{"id":"https://openalex.org/C44104985","wikidata":"https://www.wikidata.org/wiki/Q492886","display_name":"Supply chain management","level":3,"score":0.4706999957561493},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.4244999885559082},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.39660000801086426},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.375900000333786},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3221000134944916},{"id":"https://openalex.org/C192639820","wikidata":"https://www.wikidata.org/wiki/Q1114469","display_name":"Supply chain risk management","level":5,"score":0.3197999894618988},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.28760001063346863},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.28619998693466187},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.2581000030040741},{"id":"https://openalex.org/C48840187","wikidata":"https://www.wikidata.org/wiki/Q689042","display_name":"Service management","level":4,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.371","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.371","pdf_url":"https://aclanthology.org/2026.findings-acl.371.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.371","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.371","pdf_url":"https://aclanthology.org/2026.findings-acl.371.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166829324.pdf","grobid_xml":"https://content.openalex.org/works/W7166829324.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"shown":[5],"promise":[6],"in":[7,31,44,66,75,112,122],"complex":[8],"reasoning":[9],"and":[10,61,97,116],"tool-based":[11,63],"decision":[12],"making,":[13],"motivating":[14],"their":[15],"application":[16],"to":[17],"real-world":[18,52,113],"supply":[19,22,57,124],"chain":[20,23,58,125],"management.However,":[21],"workflows":[24],"require":[25],"reliable":[26,109],"long-horizon,":[27],"multi-step":[28],"orchestration":[29,64,111],"grounded":[30,65],"domain-specific":[32],"procedures,":[33],"which":[34],"remains":[35],"challenging":[36],"for":[37,91,107,120],"current":[38],"models.To":[39],"systematically":[40],"evaluate":[41],"LLM":[42],"performance":[43],"this":[45],"setting,":[46],"we":[47],"introduce":[48],"SupChain-Bench,":[49],"a":[50,104],"unified":[51],"benchmark":[53,106],"that":[54,86],"assesses":[55],"both":[56],"domain":[59],"knowledge":[60],"longhorizon":[62],"standard":[67],"operating":[68],"procedures":[69,90],"(SOPs).Our":[70],"experiments":[71],"reveal":[72],"substantial":[73],"gaps":[74],"execution":[76],"reliability":[77],"across":[78],"models.We":[79],"further":[80],"propose":[81],"SupChain-ReAct,":[82],"an":[83],"SOP-free":[84],"framework":[85],"autonomously":[87],"synthesizes":[88],"executable":[89],"tool":[92],"use,":[93],"achieving":[94],"the":[95],"strongest":[96],"most":[98],"consistent":[99],"tool-calling":[100],"performance.Our":[101],"work":[102],"establishes":[103],"principled":[105],"studying":[108],"long-horizon":[110],"operational":[114],"settings":[115],"highlights":[117],"significant":[118],"room":[119],"improvement":[121],"LLM-based":[123],"agents.":[126]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
