{"id":"https://openalex.org/W4415538016","doi":"https://doi.org/10.1145/3746027.3755790","title":"MPCC: A Novel Benchmark for Multimodal Planning with Complex Constraints in Multimodal Large Language Models","display_name":"MPCC: A Novel Benchmark for Multimodal Planning with Complex Constraints in Multimodal Large Language Models","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538016","doi":"https://doi.org/10.1145/3746027.3755790"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755790","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016506556","display_name":"Yuan\u2010Zhao Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiyan Ji","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, Heilongjiang, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113386215","display_name":"Haoran Chen","orcid":"https://orcid.org/0009-0001-3650-1646"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Chen","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, Heilongjiang, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103207823","display_name":"Qiguang Chen","orcid":"https://orcid.org/0000-0002-9154-7858"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiguang Chen","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, Heilongjiang, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025339030","display_name":"C.-P. Wu","orcid":"https://orcid.org/0009-0000-5207-4173"},"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":"Chengyue Wu","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, China"],"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/A5029082837","display_name":"Libo Qin","orcid":"https://orcid.org/0000-0002-3619-675X"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Libo Qin","raw_affiliation_strings":["School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019108029","display_name":"Wanxiang Che","orcid":"https://orcid.org/0000-0002-3907-0335"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanxiang Che","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, Heilongjiang, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, Heilongjiang, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5016506556"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1632633,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5188","last_page":"5197"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9947999715805054,"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":0.9932000041007996,"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":0.7304999828338623},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6078000068664551},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.599399983882904},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5045999884605408},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4244999885559082},{"id":"https://openalex.org/keywords/constraint-satisfaction","display_name":"Constraint satisfaction","score":0.36500000953674316},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.3440000116825104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7436000108718872},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7304999828338623},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6078000068664551},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.599399983882904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5339000225067139},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5045999884605408},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4528999924659729},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C44616089","wikidata":"https://www.wikidata.org/wiki/Q30158686","display_name":"Constraint satisfaction","level":3,"score":0.36500000953674316},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755790","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2164298032","https://openalex.org/W4403791888","https://openalex.org/W4413147807"],"related_works":[],"abstract_inverted_index":{"Multimodal":[0,62],"planning":[1,44],"capabilities":[2],"refer":[3],"to":[4,7,71,76,124,161],"the":[5,68,84,102,188],"ability":[6,75],"predict,":[8],"reason,":[9],"and":[10,25,46,97,112,164,186],"design":[11],"steps":[12],"for":[13,22,190,195],"task":[14],"execution":[15],"with":[16,64,117],"multimodal":[17,42,78,167,177],"context,":[18],"which":[19],"is":[20],"essential":[21],"complex":[23,107],"reasoning":[24,194],"decision-making":[26],"across":[27,54],"multiple":[28],"steps.":[29],"However,":[30],"current":[31],"benchmarks":[32],"face":[33],"two":[34],"key":[35],"challenges:":[36,139],"(1)":[37],"they":[38,48],"cannot":[39],"directly":[40],"assess":[41],"real-world":[43,91,196],"capabilities,":[45],"(2)":[47],"lack":[49],"constraints":[50,53,79,108,178],"or":[51],"implicit":[52],"modalities.":[55],"To":[56,82,100],"address":[57,83],"these":[58,115],"issues,":[59],"we":[60,105,154],"introduce":[61,106],"Planning":[63],"Complex":[65],"Constraints":[66],"(MPCC),":[67],"first":[69,85],"benchmark":[70],"systematically":[72],"evaluate":[73],"MLLMs'":[74],"handle":[77],"in":[80,114,171,179,192],"planning.":[81],"challenge,":[86,104],"MPCC":[87],"focuses":[88],"on":[89,133],"three":[90],"tasks:":[92],"Flight":[93],"Planning,":[94,96],"Calendar":[95],"Meeting":[98],"Planning.":[99],"solve":[101],"second":[103],"(e.g.":[109],"budget,":[110],"temporal,":[111],"spatial)":[113],"tasks,":[116],"graded":[118],"difficulty":[119],"levels":[120],"(EASY,":[121],"MEDIUM,":[122],"HARD)":[123],"separate":[125],"constraint":[126,162],"complexity":[127,163],"from":[128],"search":[129],"space":[130],"expansion.":[131],"Experiments":[132],"13":[134],"advanced":[135],"MLLMs":[136,157],"reveal":[137],"significant":[138],"closed-source":[140],"models":[141,149],"achieve":[142],"only":[143],"21.3%":[144],"feasible":[145],"plans,":[146],"while":[147],"open-source":[148],"average":[150],"below":[151],"11%.":[152],"Additionally,":[153],"observe":[155],"that":[156,165],"are":[158],"highly":[159],"sensitive":[160],"traditional":[166],"prompting":[168],"strategies":[169],"fail":[170],"multi-constraint":[172],"scenarios.":[173],"Our":[174],"work":[175],"formalizes":[176],"planning,":[180],"provides":[181],"a":[182],"rigorous":[183],"evaluation":[184],"framework,":[185],"highlights":[187],"need":[189],"advancements":[191],"constraint-aware":[193],"MLLM":[197],"applications.":[198]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}
