{"id":"https://openalex.org/W4405095661","doi":"https://doi.org/10.1007/s11263-026-02826-y","title":"EgoPlan-Bench2: A Benchmark for Multimodal Large Language Model Planning in Real-World Scenarios","display_name":"EgoPlan-Bench2: A Benchmark for Multimodal Large Language Model Planning in Real-World Scenarios","publication_year":2026,"publication_date":"2026-04-08","ids":{"openalex":"https://openalex.org/W4405095661","doi":"https://doi.org/10.1007/s11263-026-02826-y"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-026-02826-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02826-y","pdf_url":null,"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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s11263-026-02826-y","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115024197","display_name":"Lu Qiu","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":"Lu Qiu","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100728316","display_name":"Yi\u2010Ping Phoebe Chen","orcid":"https://orcid.org/0000-0002-4122-3767"},"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":"Yi Chen","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062830848","display_name":"Yuying Ge","orcid":"https://orcid.org/0000-0001-5818-2589"},"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":"Yuying Ge","raw_affiliation_strings":["ARC Lab, Tencent PCG, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047802386","display_name":"Yixiao Ge","orcid":"https://orcid.org/0000-0002-5351-5329"},"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":"Yixiao Ge","raw_affiliation_strings":["ARC Lab, Tencent PCG, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102004349","display_name":"Ying Shan","orcid":"https://orcid.org/0000-0001-7673-8325"},"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":"Ying Shan","raw_affiliation_strings":["ARC Lab, Tencent PCG, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ARC Lab, Tencent PCG, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xihui Liu","orcid":"https://orcid.org/0000-0003-1831-9952"},"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":true,"raw_author_name":"Xihui Liu","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-1831-9952","affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0057749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"134","issue":"5","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"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":0.9940000176429749,"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/T12031","display_name":"Speech and dialogue systems","score":0.9747999906539917,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7667170763015747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6103575229644775},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.1655796766281128},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.12673461437225342}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7667170763015747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6103575229644775},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1655796766281128},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.12673461437225342}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s11263-026-02826-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02826-y","pdf_url":null,"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"},{"id":"pmh:oai:arXiv.org:2412.04447","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.04447","pdf_url":"https://arxiv.org/pdf/2412.04447","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2412.04447","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.04447","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:10.1007/s11263-026-02826-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-026-02826-y","pdf_url":null,"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":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526"],"abstract_inverted_index":{"Abstract":[0],"Multimodal":[1],"Large":[2],"Language":[3],"Models":[4],"(MLLMs)":[5],"has":[6],"recently":[7],"demonstrated":[8],"superior":[9],"multimodal":[10,189,235],"comprehension":[11],"abilities,":[12],"heralding":[13],"a":[14,68,84,98,127,139,187,262],"new":[15],"era":[16],"for":[17,228],"artificial":[18],"general":[19],"intelligence":[20],"(AGI).":[21],"However,":[22],"achieving":[23],"AGI":[24],"necessitates":[25],"more":[26],"than":[27],"just":[28],"comprehension.":[29],"A":[30],"crucial":[31],"capability":[32],"required":[33],"is":[34,124,200,251],"effective":[35,254],"planning":[36,57,93,196,288],"in":[37,62,71,138,149,171,208,218],"diverse":[38,234],"scenarios,":[39,116],"which":[40],"involves":[41],"making":[42,240],"reasonable":[43],"decisions":[44],"based":[45],"on":[46,198,203,244,287],"complex":[47],"environments":[48],"to":[49,90,232,268],"solve":[50],"real-world":[51,102,172],"problems.":[52],"Despite":[53],"its":[54,266],"importance,":[55],"the":[56,92,144,176,181,226,280],"abilities":[58,231],"of":[59,74,95,101,162,183,283],"current":[60,219],"MLLMs":[61,96,156],"varied":[63],"scenarios":[64,103],"remain":[65],"underexplored,":[66],"leaving":[67],"significant":[69,169],"gap":[70],"our":[72],"understanding":[73],"their":[75,163],"full":[76],"potential.":[77],"In":[78],"this":[79,245],"paper,":[80],"we":[81,179,247],"introduce":[82],"EgoPlan-Bench2,":[83],"rigorous":[85],"and":[86,113,157,212,216,237,261,273,294],"comprehensive":[87],"benchmark":[88],"designed":[89],"assess":[91],"capabilities":[94],"across":[97],"wide":[99],"range":[100],".":[104,299],"EgoPlan-Bench2":[105,199,250],"encompasses":[106],"everyday":[107,150],"tasks":[108],"spanning":[109],"4":[110],"major":[111],"domains":[112],"24":[114],"detailed":[115],"closely":[117],"aligned":[118],"with":[119,259,272],"human":[120],"daily":[121],"life.":[122,151],"It":[123],"constructed":[125],"through":[126],"semi-automatic":[128],"process":[129],"utilizing":[130],"egocentric":[131],"videos,":[132],"complemented":[133],"by":[134],"manual":[135],"verification.":[136],"Grounded":[137],"first-person":[140],"perspective,":[141],"it":[142],"mirrors":[143],"way":[145],"humans":[146,217],"approach":[147],"problem-solving":[148],"We":[152,192,290],"evaluate":[153],"25":[154],"competitive":[155],"provide":[158],"an":[159,253],"in-depth":[160],"analysis":[161,238],"limitations,":[164],"revealing":[165],"that":[166,194,249],"they":[167],"face":[168],"challenges":[170],"planning.":[173],"To":[174],"diagnose":[175],"underlying":[177],"bottlenecks,":[178],"investigate":[180],"effectiveness":[182],"various":[184],"prompts":[185],"via":[186],"training-free":[188],"prompting":[190],"method.":[191],"find":[193],"MLLMs\u2019":[195],"performance":[197],"critically":[201],"dependent":[202],"temporally":[204],"structured":[205],"action":[206],"sequences":[207],"historical":[209],"task":[210],"progress":[211],"interactions":[213],"between":[214,270],"objects":[215],"observation":[220],"state.":[221],"This":[222],"dependency":[223],"also":[224,252],"underscores":[225],"necessity":[227],"strong":[229],"reasoning":[230,256,277,286],"integrate":[233],"cues":[236],"before":[239],"final":[241],"decision.":[242],"Building":[243],"insight,":[246],"demonstrate":[248],"video":[255],"benchmark.":[257],"Experiments":[258],"Gemini-2.5-Flash":[260],"post-trained":[263],"Qwen-2.5-VL":[264],"confirm":[265],"ability":[267],"distinguish":[269],"models":[271],"without":[274],"explicit":[275],"deliberate":[276],"mechanisms,":[278],"showcasing":[279],"tangible":[281],"impact":[282],"DeepSeek-R1":[284],"paradigm":[285],"tasks.":[289],"have":[291],"made":[292],"data":[293],"code":[295],"available":[296],"at":[297],"https://qiulu66.github.io/egoplanbench2/":[298]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}