{"id":"https://openalex.org/W4417148752","doi":"https://doi.org/10.18653/v1/2026.findings-acl.208","title":"AVA: Attentive VLM Agent for Mastering StarCraft II","display_name":"AVA: Attentive VLM Agent for Mastering StarCraft II","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417148752","doi":"https://doi.org/10.18653/v1/2026.findings-acl.208"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.208","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.208","pdf_url":null,"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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/2026.findings-acl.208","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085801402","display_name":"Wenjing Ma","orcid":"https://orcid.org/0000-0001-8757-651X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiyu Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102678888","display_name":"Yuqian Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuqian Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086192358","display_name":"Zecheng Zhang","orcid":"https://orcid.org/0000-0001-9240-1829"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zecheng Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024763828","display_name":"Bernard Ghanem","orcid":"https://orcid.org/0000-0002-5534-587X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bernard Ghanem","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100759678","display_name":"Guohao Li","orcid":"https://orcid.org/0000-0003-0260-5129"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guohao Li","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":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03314182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4270","last_page":"4290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.611299991607666,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.611299991607666,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.17190000414848328,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.09300000220537186,"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/task","display_name":"Task (project management)","score":0.5440999865531921},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4296000003814697},{"id":"https://openalex.org/keywords/battlefield","display_name":"Battlefield","score":0.392300009727478},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.388700008392334},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.385699987411499},{"id":"https://openalex.org/keywords/intelligent-agent","display_name":"Intelligent agent","score":0.3734000027179718},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.366100013256073},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.353300005197525},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.350600004196167},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.33899998664855957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6144000291824341},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5440999865531921},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5238999724388123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5121999979019165},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C2779669469","wikidata":"https://www.wikidata.org/wiki/Q4895508","display_name":"Battlefield","level":2,"score":0.392300009727478},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.385699987411499},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33899998664855957},{"id":"https://openalex.org/C20854674","wikidata":"https://www.wikidata.org/wiki/Q4386060","display_name":"Cognitive architecture","level":3,"score":0.3382999897003174},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3239000141620636},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.30070000886917114},{"id":"https://openalex.org/C5894958","wikidata":"https://www.wikidata.org/wiki/Q2297769","display_name":"Software agent","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C137703981","wikidata":"https://www.wikidata.org/wiki/Q4692093","display_name":"Agent architecture","level":3,"score":0.2709999978542328},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.208","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.208","pdf_url":null,"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"},{"id":"pmh:oai:arXiv.org:2503.05383","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2503.05383","pdf_url":"https://arxiv.org/pdf/2503.05383","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,"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"},{"id":"doi:10.48550/arxiv.2503.05383","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.05383","pdf_url":null,"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,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.208","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.208","pdf_url":null,"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,59],"introduce":[1],"AVACraft,":[2],"a":[3],"multimodal":[4],"StarCraft":[5],"II":[6],"benchmark":[7],"supporting":[8],"both":[9],"Multi-Agent":[10],"Reinforcement":[11],"Learning":[12],"(MARL)":[13],"and":[14,28,38,47,56,79,85,116],"Vision-Language":[15],"Model":[16],"(VLM)":[17],"paradigms.":[18],"Unlike":[19],"SMAC-family":[20],"environments":[21],"that":[22],"rely":[23],"on":[24],"abstract":[25],"state":[26,40],"representations":[27],"exclude":[29],"VLMs,":[30],"AVACraft":[31],"provides":[32],"RGB":[33],"visuals,":[34],"natural":[35],"language":[36],"observations,":[37],"structured":[39],"information,":[41],"enabling":[42],"systematic":[43],"comparison":[44],"between":[45,110],"training-based":[46],"zero-shot":[48,105],"methods":[49],"across":[50],"21":[51],"scenarios":[52],"spanning":[53],"micromanagement,":[54],"coordination,":[55],"strategic":[57],"planning.":[58],"establish":[60],"comprehensive":[61],"baselines:":[62],"six":[63],"MARL":[64],"algorithms":[65],"(IQL,":[66],"QMIX,":[67],"QTRAN,":[68],"VDN,":[69],"MAPPO,":[70],"IPPO)":[71],"with":[72,106],"Swin-Transformer":[73],"backbones":[74],"trained":[75],"for":[76],"5M":[77,99],"steps,":[78,100],"multiple":[80],"VLMs":[81,102],"including":[82],"proprietary":[83],"(GPT-4o)":[84],"open-source":[86],"(Qwen3-VL)":[87],"models.":[88],"Results":[89],"reveal":[90],"complementary":[91],"strengths-MARL":[92],"peaks":[93],"at":[94],"19.3%":[95],"win":[96],"rate":[97],"after":[98],"while":[101],"achieve":[103],"75-90%":[104],"human-aligned":[107],"decisions-exposing":[108],"trade-offs":[109],"training":[111],"efficiency,":[112],"performance":[113],"ceilings,":[114],"interpretability,":[115],"deployment":[117],"cost.":[118],"Code:":[119],"https://github.com/camel-ai/VLM-Play-StarCraft2.":[120]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}