{"id":"https://openalex.org/W7138403479","doi":"https://doi.org/10.1609/aaai.v40i10.37800","title":"Game Ground Bench: Probing the Limits of LVLMs in Complex Semantic Grounding Across Game Universes","display_name":"Game Ground Bench: Probing the Limits of LVLMs in Complex Semantic Grounding Across Game Universes","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138403479","doi":"https://doi.org/10.1609/aaai.v40i10.37800"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i10.37800","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37800","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i10.37800","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081854739","display_name":"Zhangyang Qi","orcid":"https://orcid.org/0009-0000-6923-6220"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhangyang Qi","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129658881","display_name":"jinsong li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinsong Li","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129737180","display_name":"Hongjian Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongjian Wu","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129704764","display_name":"Jiaqi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Wang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129728866","display_name":"Hengshuang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hengshuang Zhao","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"10","first_page":"8493","last_page":"8501"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8751999735832214,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8751999735832214,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.032099999487400055,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.011800000444054604,"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/generalization","display_name":"Generalization","score":0.6503000259399414},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5473999977111816},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5224999785423279},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.4731999933719635},{"id":"https://openalex.org/keywords/common-ground","display_name":"Common ground","score":0.4205000102519989},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.40450000762939453},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.39480000734329224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7838000059127808},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6503000259399414},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5473999977111816},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5224999785423279},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.4731999933719635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45489999651908875},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4320000112056732},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.4205000102519989},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.39480000734329224},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.35499998927116394},{"id":"https://openalex.org/C3018412434","wikidata":"https://www.wikidata.org/wiki/Q7889","display_name":"Video game","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32839998602867126},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C3017957056","wikidata":"https://www.wikidata.org/wiki/Q1331296","display_name":"Game play","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2547000050544739},{"id":"https://openalex.org/C503285160","wikidata":"https://www.wikidata.org/wiki/Q858057","display_name":"Game design","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i10.37800","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37800","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37800","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i10.37800","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i10.37800","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4377606511116028,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Vision-Language":[1],"Models":[2],"(LVLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"capabilities,":[7],"yet":[8],"their":[9],"ability":[10],"to":[11,61,80,124,150],"ground":[12],"language":[13,122],"in":[14,87,145,220,227],"complex,":[15],"interactive":[16],"environments":[17],"such":[18],"as":[19],"video":[20],"games":[21],"remains":[22],"a":[23,38,75,108,168,209],"critical":[24],"frontier.":[25],"Existing":[26],"benchmarks":[27,42,53],"are":[28,54],"inadequate":[29],"for":[30,156,215],"this":[31,69,228],"purpose:":[32],"real-world":[33],"datasets":[34],"like":[35],"RefCOCO":[36],"introduce":[37],"domain":[39],"gap;":[40],"GUI-centric":[41],"lack":[43],"the":[44,82,174],"complexity":[45],"of":[46,85,110],"modern":[47],"game":[48,147],"interfaces;":[49],"and":[50,104,128,187,211],"existing":[51,134,200],"game-specific":[52],"often":[55],"too":[56],"simplistic":[57],"or":[58],"narrow,":[59],"failing":[60],"assess":[62],"fine-grained,":[63],"generalizable":[64],"grounding":[65,83,142],"capabilities.":[66],"To":[67,162],"address":[68,163],"issue,":[70],"we":[71,165],"propose":[72,166],"GGBench":[73,91,207],"\u2014":[74],"large-scale,":[76],"cross-genre":[77],"benchmark":[78],"designed":[79],"probe":[81],"capabilities":[84],"LVLMs":[86,201],"diverse":[88],"gaming":[89,157,221],"scenarios.":[90,148],"features":[92],"unprecedented":[93],"genre":[94],"diversity,":[95],"encompassing":[96],"10":[97],"categories":[98],"including":[99],"card":[100],"games,":[101,106],"first-person":[102],"shooters,":[103],"role-playing":[105],"with":[107,140],"total":[109],"1335":[111],"test":[112],"images.":[113],"It":[114],"focuses":[115],"on":[116,138,173,202,218],"tasks":[117],"that":[118],"require":[119],"connecting":[120],"natural":[121],"instructions":[123],"specific":[125],"in-game":[126],"objects":[127],"UI":[129],"elements.":[130],"Experimental":[131],"results":[132],"show":[133,196],"models":[135],"perform":[136],"poorly":[137],"GGBench,":[139,203],"weak":[141],"abilities,":[143],"especially":[144],"complex":[146],"Due":[149],"limited":[151,183],"data":[152,185],"scale,":[153],"fine-tuning":[154],"them":[155],"scenarios":[158],"is":[159],"also":[160],"challenging.":[161],"this,":[164],"Game-R1,":[167],"novel":[169],"training":[170],"method":[171],"centered":[172],"Grounded":[175],"Reinforcement":[176],"Policy":[177],"Optimization":[178],"(GRPO)":[179],"algorithm.":[180],"GRPO":[181],"maximizes":[182],"interaction":[184],"utility":[186],"enables":[188],"robust":[189],"few-shot":[190],"generalization":[191],"across":[192],"games.":[193],"Extensive":[194],"experiments":[195],"Game-R1":[197],"significantly":[198],"outperforms":[199],"validating":[204],"our":[205],"approach.":[206],"provides":[208],"solid":[210],"comprehensive":[212],"evaluation":[213],"platform":[214],"subsequent":[216],"research":[217],"agents":[219],"environments,":[222],"which":[223],"strongly":[224],"promotes":[225],"development":[226],"field.":[229]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}