{"id":"https://openalex.org/W4415541296","doi":"https://doi.org/10.1145/3746027.3760212","title":"Reasoning and Planning for Multimodal Large Language Models: A Multilingual and Cross-Domain Exploration","display_name":"Reasoning and Planning for Multimodal Large Language Models: A Multilingual and Cross-Domain Exploration","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415541296","doi":"https://doi.org/10.1145/3746027.3760212"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3760212","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3760212","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":"conference-paper","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/A5089770162","display_name":"Sarmistha Das","orcid":"https://orcid.org/0000-0001-6608-0400"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sarmistha Das","raw_affiliation_strings":["Indian Institute of Technology Patna, Patna, India"],"raw_orcid":"https://orcid.org/0000-0001-6608-0400","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna, Patna, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109494520","display_name":"Akash Ghosh","orcid":"https://orcid.org/0009-0001-9353-7258"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Akash Ghosh","raw_affiliation_strings":["Indian Institute of Technology Patna, Patna, India"],"raw_orcid":"https://orcid.org/0009-0001-9353-7258","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna, Patna, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060797340","display_name":"Sriparna Saha","orcid":"https://orcid.org/0000-0001-5458-9381"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriparna Saha","raw_affiliation_strings":["Indian Institute of Technology Patna, Patna, India"],"raw_orcid":"https://orcid.org/0000-0001-5458-9381","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Patna, Patna, India","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083954626","display_name":"Koustava Goswami","orcid":"https://orcid.org/0000-0002-0428-160X"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Koustava Goswami","raw_affiliation_strings":["Adobe Research, San Jose, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0428-160X","affiliations":[{"raw_affiliation_string":"Adobe Research, San Jose, CA, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120132644","display_name":"Joseph K.J","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joseph K.J","raw_affiliation_strings":["Adobe Research, Bangalore, India"],"raw_orcid":"https://orcid.org/0000-0003-1168-1609","affiliations":[{"raw_affiliation_string":"Adobe Research, Bangalore, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":null,"issue":null,"first_page":"14342","last_page":"14343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9921000003814697,"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":0.9921000003814697,"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":0.9697999954223633,"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":0.9520000219345093,"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/key","display_name":"Key (lock)","score":0.5476999878883362},{"id":"https://openalex.org/keywords/session","display_name":"Session (web analytics)","score":0.5026000142097473},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.4226999878883362},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.4025000035762787},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.40230000019073486},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.33500000834465027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.711899995803833},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.5026000142097473},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.4025000035762787},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3528999984264374},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.33500000834465027},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31540000438690186},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2930000126361847},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.288100004196167},{"id":"https://openalex.org/C2780035574","wikidata":"https://www.wikidata.org/wiki/Q30081","display_name":"Multilingualism","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C14224292","wikidata":"https://www.wikidata.org/wiki/Q13600188","display_name":"Conceptual framework","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3760212","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3760212","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,50,86],"Multimodal":[3],"Large":[4],"Language":[5],"Models":[6],"(MLLMs),":[7],"coupled":[8],"with":[9,42,99],"the":[10,32,58,75,100],"progress":[11],"of":[12,39,63],"reinforcement":[13],"learning,":[14],"have":[15],"substantially":[16],"enhanced":[17,82],"reasoning":[18,48,66,83,111],"and":[19,27,36,52,61,84,88,97,103],"decision-making":[20],"across":[21],"modalities,":[22],"including":[23],"text,":[24],"vision,":[25],"audio,":[26],"video.":[28],"This":[29],"tutorial":[30],"introduces":[31],"fundamental":[33],"principles,":[34],"methodologies,":[35],"practical":[37,104],"applications":[38],"MLLM":[40,110],"reasoning,":[41],"a":[43],"particular":[44],"emphasis":[45],"on":[46],"strengthening":[47],"capabilities":[49],"multilingual":[51],"cross-domain":[53,89],"settings.":[54],"We":[55],"further":[56],"discuss":[57],"key":[59],"challenges":[60],"limitations":[62],"current":[64],"multimodal":[65],"approaches,":[67],"as":[68,70],"well":[69],"future":[71],"directions":[72],"for":[73],"advancing":[74],"field.":[76],"By":[77],"highlighting":[78],"how":[79],"MLLMs":[80],"support":[81],"planning":[85],"cross-lingual":[87],"contexts,":[90],"this":[91],"session":[92],"aims":[93],"to":[94,107],"equip":[95],"researchers":[96],"practitioners":[98],"conceptual":[101],"foundations":[102],"tools":[105],"needed":[106],"effectively":[108],"integrate":[109],"into":[112],"their":[113],"work.":[114]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}
