{"id":"https://openalex.org/W4413321791","doi":"https://doi.org/10.1109/cog64752.2025.11114387","title":"PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments","display_name":"PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments","publication_year":2025,"publication_date":"2025-08-19","ids":{"openalex":"https://openalex.org/W4413321791","doi":"https://doi.org/10.1109/cog64752.2025.11114387"},"language":"en","primary_location":{"id":"doi:10.1109/cog64752.2025.11114387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog64752.2025.11114387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.06235","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119347983","display_name":"Olivier Schipper","orcid":null},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Olivier Schipper","raw_affiliation_strings":["Eindhoven University of Technology,Department of Mathematics and Computer Science,Eindhoven,Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology,Department of Mathematics and Computer Science,Eindhoven,Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100725640","display_name":"Yudi Zhang","orcid":"https://orcid.org/0000-0002-7830-5133"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yudi Zhang","raw_affiliation_strings":["Eindhoven University of Technology,Department of Mathematics and Computer Science,Eindhoven,Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology,Department of Mathematics and Computer Science,Eindhoven,Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101806970","display_name":"Yali Du","orcid":"https://orcid.org/0000-0001-5908-354X"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yali Du","raw_affiliation_strings":["King's College London,Department of Informatics,London,UK"],"affiliations":[{"raw_affiliation_string":"King's College London,Department of Informatics,London,UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022601535","display_name":"Mykola Pechenizkiy","orcid":"https://orcid.org/0000-0003-4955-0743"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mykola Pechenizkiy","raw_affiliation_strings":["Eindhoven University of Technology,Department of Mathematics and Computer Science,Eindhoven,Netherlands"],"affiliations":[{"raw_affiliation_string":"Eindhoven University of Technology,Department of Mathematics and Computer Science,Eindhoven,Netherlands","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087456682","display_name":"Fang Meng","orcid":"https://orcid.org/0000-0002-7595-5018"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Meng Fang","raw_affiliation_strings":["University of Liverpool,Department of Computer Science,Liverpool,UK"],"affiliations":[{"raw_affiliation_string":"University of Liverpool,Department of Computer Science,Liverpool,UK","institution_ids":["https://openalex.org/I146655781"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5119347983"],"corresponding_institution_ids":["https://openalex.org/I83019370"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25104567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12203","display_name":"Mobile Agent-Based Network Management","score":0.9887999892234802,"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"}},"topics":[{"id":"https://openalex.org/T12203","display_name":"Mobile Agent-Based Network Management","score":0.9887999892234802,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9807999730110168,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9674999713897705,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/benchmarking","display_name":"Benchmarking","score":0.9190402030944824},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6237692832946777},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3930858075618744},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.37474000453948975},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.19101816415786743},{"id":"https://openalex.org/keywords/marketing","display_name":"Marketing","score":0.04243305325508118}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.9190402030944824},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6237692832946777},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3930858075618744},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.37474000453948975},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.19101816415786743},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.04243305325508118}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cog64752.2025.11114387","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cog64752.2025.11114387","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},{"id":"pmh:oai:kclpure.kcl.ac.uk:publications/5228c643-d96c-4398-8f0c-99d98aa58174","is_oa":false,"landing_page_url":"https://kclpure.kcl.ac.uk/portal/en/publications/5228c643-d96c-4398-8f0c-99d98aa58174","pdf_url":null,"source":{"id":"https://openalex.org/S4306400216","display_name":"Research Portal (King's College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I183935753","host_organization_name":"King's College London","host_organization_lineage":["https://openalex.org/I183935753"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Schipper, O, Zhang, Y, Du, Y, Pechenizkiy, M & Fang, M 2025, 'PillagerBench : Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments', IEEE Conference on Computatonal Intelligence and Games, CIG. https://doi.org/10.1109/CoG64752.2025.11114387","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.tue.nl:publications/cc7b7982-d471-448d-a315-ec8bc0e06a2a","is_oa":false,"landing_page_url":"https://research.tue.nl/en/publications/cc7b7982-d471-448d-a315-ec8bc0e06a2a","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Schipper, O, Zhang, Y, Du, Y, Pechenizkiy, M & Fang, M 2025, PillagerBench : Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments. in IEEE 2025 Conference on Games, CoG 2025., 11114387, IEEE Computer Society, 2025 IEEE Conference on Games, CoG 2025, Lisbon, Portugal, 26/08/25. https://doi.org/10.1109/CoG64752.2025.11114387","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:2509.06235","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.06235","pdf_url":"https://arxiv.org/pdf/2509.06235","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"pmh:oai:arXiv.org:2509.06235","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.06235","pdf_url":"https://arxiv.org/pdf/2509.06235","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1607078431","https://openalex.org/W4302423442","https://openalex.org/W4393065402","https://openalex.org/W4411119815"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699"],"abstract_inverted_index":{"LLM-based":[0,62],"agents":[1],"have":[2,111],"shown":[3],"promise":[4],"in":[5,15,35,40,116],"various":[6],"cooperative":[7],"and":[8,49,74,87,99],"strategic":[9,100],"reasoning":[10],"tasks,":[11],"but":[12],"their":[13],"effectiveness":[14],"competitive":[16,37,120],"multi-agent":[17,33,63,117],"environments":[18],"remains":[19],"underexplored.":[20],"To":[21,106],"address":[22],"this":[23],"gap,":[24],"we":[25,94,110],"introduce":[26],"PillagerBench,":[27,113],"a":[28],"novel":[29],"framework":[30],"for":[31,53,119],"evaluating":[32],"systems":[34],"real-time":[36],"team-vs-team":[38],"scenarios":[39],"Minecraft.":[41],"It":[42],"provides":[43],"an":[44,61],"extensible":[45],"API,":[46],"multi-round":[47],"testing,":[48],"rule-based":[50],"built-in":[51],"opponents":[52],"fair,":[54],"reproducible":[55],"comparisons.":[56],"We":[57],"also":[58],"propose":[59],"TactiCrafter,":[60],"system":[64],"that":[65,82],"facilitates":[66],"teamwork":[67],"through":[68,91],"human-readable":[69],"tactics,":[70],"learns":[71],"causal":[72],"dependencies,":[73],"adapts":[75],"to":[76],"opponent":[77],"strategies.":[78],"Our":[79],"evaluation":[80],"demonstrates":[81],"TactiCrafter":[83],"outperforms":[84],"baseline":[85],"approaches":[86],"showcases":[88],"adaptive":[89],"learning":[90,97],"self-play.":[92],"Additionally,":[93],"analyze":[95],"its":[96],"process":[98],"evolution":[101],"over":[102],"multiple":[103],"game":[104],"episodes.":[105],"encourage":[107],"further":[108],"research,":[109],"open-sourced":[112],"fostering":[114],"advancements":[115],"AI":[118],"environments.":[121]},"counts_by_year":[],"updated_date":"2026-03-08T08:50:53.379069","created_date":"2025-10-10T00:00:00"}