{"id":"https://openalex.org/W4412887847","doi":"https://doi.org/10.18653/v1/2025.findings-acl.988","title":"X-WebAgentBench: A Multilingual Interactive Web Benchmark for Evaluating Global Agentic System","display_name":"X-WebAgentBench: A Multilingual Interactive Web Benchmark for Evaluating Global Agentic System","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887847","doi":"https://doi.org/10.18653/v1/2025.findings-acl.988"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.988","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.988","pdf_url":"https://aclanthology.org/2025.findings-acl.988.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 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.988.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058176560","display_name":"Peng Wang","orcid":"https://orcid.org/0000-0001-8782-857X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ruihan Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruihan Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103207823","display_name":"Qiguang Chen","orcid":"https://orcid.org/0000-0002-9154-7858"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiguang Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081386315","display_name":"Mengkang Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengkang Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5029082837","display_name":"Libo Qin","orcid":"https://orcid.org/0000-0002-3619-675X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Libo Qin","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":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19320","last_page":"19335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.948199987411499,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.948199987411499,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9110000133514404,"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/computer-science","display_name":"Computer science","score":0.7720175981521606},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7610797882080078},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5074748396873474},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32062268257141113}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7720175981521606},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7610797882080078},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5074748396873474},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32062268257141113},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.988","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.988","pdf_url":"https://aclanthology.org/2025.findings-acl.988.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 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.988","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.988","pdf_url":"https://aclanthology.org/2025.findings-acl.988.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 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321514","display_name":"Central South University","ror":"https://ror.org/00f1zfq44"},{"id":"https://openalex.org/F4320324720","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12"},{"id":"https://openalex.org/F4320335581","display_name":"Young Scientists Fund","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887847.pdf","grobid_xml":"https://content.openalex.org/works/W4412887847.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526"],"abstract_inverted_index":{"Recently,":[0],"large":[1],"language":[2,47,84],"model":[3],"(LLM)-based":[4],"agents":[5,48,85],"have":[6],"achieved":[7],"significant":[8,14],"success":[9],"in":[10,71,112,146],"interactive":[11,73],"environments,":[12],"attracting":[13],"academic":[15],"and":[16,80,105],"industrial":[17],"attention.Despite":[18],"these":[19],"advancements,":[20],"current":[21],"research":[22],"predominantly":[23],"focuses":[24],"on":[25],"English":[26],"scenarios.In":[27],"reality,":[28],"there":[29],"are":[30],"over":[31],"7,000":[32],"languages":[33],"worldwide,":[34],"all":[35],"of":[36,46,56,83,94,102],"which":[37,76],"demand":[38],"access":[39],"to":[40,91,129],"comparable":[41],"agentic":[42,58],"services.Nevertheless,":[43],"the":[44,53,78,92,100],"development":[45],"remains":[49],"inadequate":[50],"for":[51,142],"meeting":[52],"diverse":[54],"requirements":[55],"multilingual":[57,68,143],"applications.To":[59],"fill":[60],"this":[61],"gap,":[62],"we":[63,98],"introduce":[64],"X-WebAgentBench,":[65],"a":[66,139],"novel":[67],"agent":[69,96,144],"benchmark":[70,141],"an":[72],"web":[74],"environment,":[75],"evaluates":[77],"planning":[79],"interaction":[81],"performance":[82,101],"across":[86],"multiple":[87],"languages,":[88],"thereby":[89],"contributing":[90],"advancement":[93],"global":[95],"intelligence.Additionally,":[97],"assess":[99],"various":[103],"LLMs":[104],"cross-lingual":[106],"alignment":[107],"methods,":[108],"examining":[109],"their":[110],"effectiveness":[111],"enhancing":[113],"agents.Our":[114],"findings":[115],"reveal":[116],"that":[117,134],"even":[118],"advanced":[119],"models":[120],"like":[121],"GPT-4o,":[122],"when":[123],"combined":[124],"with":[125],"crosslingual":[126],"techniques,":[127],"fail":[128],"achieve":[130],"satisfactory":[131],"results.We":[132],"hope":[133],"X-WebAgentBench":[135],"can":[136],"serve":[137],"as":[138],"valuable":[140],"scenario":[145],"real-world":[147],"applications.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}