{"id":"https://openalex.org/W7128730772","doi":"https://doi.org/10.1007/s11263-025-02676-0","title":"EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning","display_name":"EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning","publication_year":2026,"publication_date":"2026-02-12","ids":{"openalex":"https://openalex.org/W7128730772","doi":"https://doi.org/10.1007/s11263-025-02676-0"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-025-02676-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02676-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02676-0.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02676-0.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101508336","display_name":"Yuehua Chen","orcid":"https://orcid.org/0000-0002-4646-4017"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"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":"Yi Chen","raw_affiliation_strings":["The University of Hong Kong, HongKong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, HongKong SAR, China","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125694548","display_name":"Yuying Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuying Ge","raw_affiliation_strings":["AI Lab, Tencent, Shenzhen, 518052, Guangdong Province, China","ARC Lab, Tencent PCG, Shenzhen, 518052, Guangdong Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Lab, Tencent, Shenzhen, 518052, Guangdong Province, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"ARC Lab, Tencent PCG, Shenzhen, 518052, Guangdong Province, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125769374","display_name":"Yixiao Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yixiao Ge","raw_affiliation_strings":["AI Lab, Tencent, Shenzhen, 518052, Guangdong Province, China","ARC Lab, Tencent PCG, Shenzhen, 518052, Guangdong Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Lab, Tencent, Shenzhen, 518052, Guangdong Province, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"ARC Lab, Tencent PCG, Shenzhen, 518052, Guangdong Province, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mingyu Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingyu Ding","raw_affiliation_strings":["University of California, Berkeley, 94720, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, 94720, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451253","display_name":"Bing Li","orcid":"https://orcid.org/0000-0002-2165-2636"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"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":"Bohao Li","raw_affiliation_strings":["The University of Hong Kong, HongKong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, HongKong SAR, China","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125703286","display_name":"Rui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"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":"Rui Wang","raw_affiliation_strings":["The University of Hong Kong, HongKong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, HongKong SAR, China","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125742213","display_name":"Ruifeng Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruifeng Xu","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, 518052, Guangdong Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, 518052, Guangdong Province, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ying Shan","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]},{"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":["CN","HK"],"is_corresponding":false,"raw_author_name":"Ying Shan","raw_affiliation_strings":["ARC Lab, Tencent PCG, Shenzhen, 518052, Guangdong Province, China","The University of Hong Kong, HongKong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG, Shenzhen, 518052, Guangdong Province, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"The University of Hong Kong, HongKong SAR, China","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005952268","display_name":"Xihui Liu","orcid":"https://orcid.org/0000-0003-1831-9952"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihui Liu","raw_affiliation_strings":["AI Lab, Tencent, Shenzhen, 518052, Guangdong Province, China"],"raw_orcid":"https://orcid.org/0000-0003-1831-9952","affiliations":[{"raw_affiliation_string":"AI Lab, Tencent, Shenzhen, 518052, Guangdong Province, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5125694548","https://openalex.org/A5125769374"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":9.8969,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95978713,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"134","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6488000154495239,"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":0.6488000154495239,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.029200000688433647,"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/T10028","display_name":"Topic Modeling","score":0.027400000020861626,"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/mirroring","display_name":"Mirroring","score":0.7479000091552734},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7437999844551086},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7343999743461609},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5418000221252441},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5267000198364258},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.5049999952316284},{"id":"https://openalex.org/keywords/milestone","display_name":"Milestone","score":0.4571000039577484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8227999806404114},{"id":"https://openalex.org/C189645446","wikidata":"https://www.wikidata.org/wiki/Q350865","display_name":"Mirroring","level":2,"score":0.7479000091552734},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7437999844551086},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7343999743461609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6452999711036682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5544999837875366},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5418000221252441},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5267000198364258},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5049999952316284},{"id":"https://openalex.org/C120060458","wikidata":"https://www.wikidata.org/wiki/Q10145","display_name":"Milestone","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2964000105857849},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11263-025-02676-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02676-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02676-0.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11263-025-02676-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-025-02676-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-025-02676-0.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128730772.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1947050545","https://openalex.org/W2165605600","https://openalex.org/W2763331099","https://openalex.org/W2957775769","https://openalex.org/W2964094654","https://openalex.org/W2981635073","https://openalex.org/W3004037805","https://openalex.org/W3106768499","https://openalex.org/W3132567969","https://openalex.org/W3199332348","https://openalex.org/W3201174429","https://openalex.org/W3203256294","https://openalex.org/W3205786327","https://openalex.org/W3207758636","https://openalex.org/W4221153256","https://openalex.org/W4312446817","https://openalex.org/W4312478760","https://openalex.org/W4312769771","https://openalex.org/W4385430451","https://openalex.org/W4386065873","https://openalex.org/W4386076522","https://openalex.org/W4389519587","https://openalex.org/W4390873312","https://openalex.org/W4390873991","https://openalex.org/W4402671548","https://openalex.org/W4402716381","https://openalex.org/W4402716477","https://openalex.org/W4402727142","https://openalex.org/W4402727669","https://openalex.org/W4402727764","https://openalex.org/W4403081466","https://openalex.org/W4403587166","https://openalex.org/W6912494966"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"The":[1],"pursuit":[2],"of":[3,35,40,58,96,112,115,130,134],"artificial":[4],"general":[5],"intelligence":[6],"(AGI)":[7],"has":[8],"been":[9],"accelerated":[10],"by":[11],"Multimodal":[12],"Large":[13],"Language":[14],"Models":[15],"(MLLMs),":[16],"which":[17],"exhibit":[18],"superior":[19],"reasoning,":[20],"generalization":[21],"capabilities,":[22],"and":[23,53,123,181],"proficiency":[24],"in":[25,32,50,65,98,148],"processing":[26],"multimodal":[27],"inputs.":[28],"A":[29],"crucial":[30],"milestone":[31],"the":[33,38,62,93,110,178],"evolution":[34],"AGI":[36],"is":[37],"attainment":[39],"human-level":[41,77,152],"planning,":[42],"a":[43,55,67,88,131,143,163,182],"fundamental":[44],"ability":[45],"for":[46,146],"making":[47],"informed":[48],"decisions":[49],"complex":[51],"environments,":[52],"solving":[54],"wide":[56,132],"range":[57,133],"real-world":[59,99],"problems.":[60],"Despite":[61],"impressive":[63],"advancements":[64],"MLLMs,":[66,116],"question":[68],"remains:":[69],"How":[70],"far":[71],"are":[72],"current":[73],"MLLMs":[74,97,135,149],"from":[75,101],"achieving":[76],"planning?":[78],"To":[79,155],"shed":[80],"light":[81],"on":[82,172],"this":[83,157],"question,":[84],"we":[85,159],"introduce":[86],"EgoPlan-Bench,":[87],"comprehensive":[89],"benchmark":[90,184],"to":[91,150,189],"evaluate":[92],"planning":[94,113],"abilities":[95],"scenarios":[100],"an":[102],"egocentric":[103],"perspective,":[104],"mirroring":[105],"human":[106],"perception.":[107],"EgoPlan-Bench":[108,138],"emphasizes":[109],"evaluation":[111,129],"capabilities":[114],"featuring":[117],"realistic":[118],"tasks,":[119],"diverse":[120],"action":[121],"plans,":[122],"intricate":[124],"visual":[125],"observations.":[126],"Our":[127],"rigorous":[128],"reveals":[136],"that":[137,167],"poses":[139],"significant":[140],"challenges,":[141],"highlighting":[142],"substantial":[144],"scope":[145],"improvement":[147],"achieve":[151],"task":[153],"planning.":[154],"facilitate":[156],"advancement,":[158],"further":[160],"present":[161],"EgoPlan-IT,":[162],"specialized":[164],"instruction-tuning":[165],"dataset":[166],"effectively":[168],"enhances":[169],"model":[170],"performance":[171],"EgoPlan-Bench.":[173],"We":[174],"have":[175],"made":[176],"all":[177],"codes,":[179],"data,":[180],"maintained":[183],"leaderboard":[185],"available":[186],"at":[187],"https://chenyi99.github.io/ego_plan/":[188],"advance":[190],"future":[191],"research.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-02-13T00:00:00"}