{"id":"https://openalex.org/W4412945638","doi":"https://doi.org/10.18653/v1/2025.acl-long.421","title":"MultiAgentBench : Evaluating the Collaboration and Competition of LLM agents","display_name":"MultiAgentBench : Evaluating the Collaboration and Competition of LLM agents","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945638","doi":"https://doi.org/10.18653/v1/2025.acl-long.421"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.421","doi":"https://doi.org/10.18653/v1/2025.acl-long.421","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.421","pdf_url":"https://aclanthology.org/2025.acl-long.421.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2025.acl-long.421.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kunlun Zhu","orcid":null,"observed_orcids":[]},"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":"Kunlun Zhu","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119204562","display_name":"Hongyi Du","orcid":null,"observed_orcids":[]},"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":"Hongyi Du","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhaochen Hong","orcid":null,"observed_orcids":[]},"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":"Zhaochen Hong","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051645697","display_name":"Xiaocheng Yang","orcid":"https://orcid.org/0000-0002-9330-5828","observed_orcids":["https://orcid.org/0000-0002-9330-5828"]},"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":"Xiaocheng Yang","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shuyi Guo","orcid":null,"observed_orcids":[]},"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":"Shuyi Guo","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhe Wang","orcid":null,"observed_orcids":[]},"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":"Zhe Wang","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028682241","display_name":"Zhihua Wang","orcid":"https://orcid.org/0000-0002-7488-8298","observed_orcids":["https://orcid.org/0000-0002-7488-8298"]},"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":"Zhenhailong Wang","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100962789","display_name":"Cheng Qian","orcid":null,"observed_orcids":[]},"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":"Cheng Qian","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119204563","display_name":"Robert Tang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robert Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075033889","display_name":"Heng Ji","orcid":"https://orcid.org/0000-0002-0464-7966","observed_orcids":["https://orcid.org/0000-0002-0464-7966"]},"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":"Heng Ji","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003491365","display_name":"Jiaxuan You","orcid":"https://orcid.org/0000-0003-1812-7598","observed_orcids":["https://orcid.org/0000-0003-1812-7598"]},"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":"Jiaxuan You","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":35.4945,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.9989073,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8580","last_page":"8622"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.8920999765396118,"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":0.8920999765396118,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.015599999576807022,"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":0.012400000356137753,"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/multi-agent-systems","display_name":"multi-agent systems","score":0.8980000019073486},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.7799999713897705},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.640999972820282},{"id":"https://openalex.org/keywords/agent-cooperation","display_name":"agent cooperation","score":0.7009999752044678},{"id":"https://openalex.org/keywords/agent-competition","display_name":"agent competition","score":0.925000011920929},{"id":"https://openalex.org/keywords/coordination-protocols","display_name":"coordination protocols","score":0.8970000147819519},{"id":"https://openalex.org/keywords/graph-topology","display_name":"graph topology","score":0.7509999871253967},{"id":"https://openalex.org/keywords/group-discussion","display_name":"group discussion","score":0.6959999799728394},{"id":"https://openalex.org/keywords/cognitive-planning","display_name":"cognitive planning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/key-performance-indicators","display_name":"key performance indicators","score":0.7419999837875366},{"id":"https://openalex.org/keywords/gpt-4o-mini","display_name":"GPT-4o-mini","score":0.7540000081062317}],"concepts":[{"id":"https://openalex.org/C91306197","wikidata":"https://www.wikidata.org/wiki/Q45767","display_name":"Competition (biology)","level":2,"score":0.6693426370620728},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5045877695083618},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.043989717960357666},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.421","doi":"https://doi.org/10.18653/v1/2025.acl-long.421","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.421","pdf_url":"https://aclanthology.org/2025.acl-long.421.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.01935","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.01935","pdf_url":"https://arxiv.org/pdf/2503.01935","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"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.421","doi":"https://doi.org/10.18653/v1/2025.acl-long.421","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.421","pdf_url":"https://aclanthology.org/2025.acl-long.421.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945638.pdf","grobid_xml":"https://content.openalex.org/works/W4412945638.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4402705366","https://openalex.org/W4404782996","https://openalex.org/W4416036811","https://openalex.org/W6910724711","https://openalex.org/W7204768814","https://openalex.org/W7164042786","https://openalex.org/W4387294301","https://openalex.org/W7214615817","https://openalex.org/W4392222647","https://openalex.org/W4405266245"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"shown":[5],"remarkable":[6],"capabilities":[7],"as":[8,89],"autonomous":[9],"agents;":[10],"yet":[11],"existing":[12],"benchmarks":[13],"either":[14],"focus":[15],"on":[16],"singleagent":[17],"tasks":[18],"or":[19],"are":[20,124],"confined":[21],"to":[22,26,44],"narrow":[23],"domains,":[24],"failing":[25],"capture":[27],"the":[28,61,97,105,111],"dynamics":[29],"of":[30,63],"multi-agent":[31,47],"coordination":[32,76,108],"and":[33,65,82,85,92,122],"competition.In":[34],"this":[35],"paper,":[36],"we":[37,73],"introduce":[38],"MultiAgentBench,":[39],"a":[40],"comprehensive":[41],"benchmark":[42],"designed":[43],"evaluate":[45,74],"LLMbased":[46],"systems":[48],"across":[49],"diverse,":[50],"interactive":[51],"scenarios.Our":[52],"framework":[53],"measures":[54],"not":[55],"only":[56],"task":[57,100],"completion":[58],"but":[59],"also":[60],"quality":[62],"collaboration":[64],"competition":[66],"using":[67],"novel,":[68],"milestone-based":[69],"key":[70],"performance":[71],"indicators.Moreover,":[72],"various":[75],"protocols":[77,109],"(including":[78],"star,":[79],"chain,":[80],"tree,":[81],"graph":[83,102],"topologies)":[84],"innovative":[86],"strategies":[87],"such":[88],"group":[90],"discussion":[91],"cognitive":[93,114],"planning.Notably,":[94],"gpt-4o-mini":[95],"reaches":[96],"average":[98],"highest":[99],"score,":[101],"structure":[103],"performs":[104],"best":[106],"among":[107],"in":[110],"research":[112],"scenario,and":[113],"planning":[115],"improves":[116],"milestone":[117],"achievement":[118],"rates":[119],"by":[120],"3%.Code":[121],"datasets":[123],"publicavailable":[125],"at":[126],"https://github.com/ulab-uiuc/MARBLE.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":30},{"year":2025,"cited_by_count":8}],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2025-10-10T00:00:00"}
