{"id":"https://openalex.org/W7225203205","doi":"https://doi.org/10.20944/preprints202611.0215.v1","title":"Multimodal Reasoning, Agentic Systems, and Embedding Models: A Survey of Recent Advances","display_name":"Multimodal Reasoning, Agentic Systems, and Embedding Models: A Survey of Recent Advances","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225203205","doi":"https://doi.org/10.20944/preprints202611.0215.v1"},"language":"en","primary_location":{"id":"doi:10.20944/preprints202611.0215.v1","doi":"https://doi.org/10.20944/preprints202611.0215.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0215.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.20944/preprints202611.0215.v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075188655","display_name":"Mohammed Ayalew Belay","orcid":"https://orcid.org/0000-0003-2144-9790","observed_orcids":["https://orcid.org/0000-0003-2144-9790"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammed Ayalew Belay","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158823619","display_name":"Michael Endale","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Endale","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5119647087","display_name":"Amirshayan Haghipour","orcid":"https://orcid.org/0009-0006-2670-6337","observed_orcids":["https://orcid.org/0009-0006-2670-6337"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amirshayan Haghipour","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multimodal-reasoning","display_name":"multimodal reasoning","score":0.9539999961853027},{"id":"https://openalex.org/keywords/chain-of-thought-reasoning","display_name":"chain-of-thought reasoning","score":0.6899999976158142},{"id":"https://openalex.org/keywords/reinforcement-learning-for-reasoning","display_name":"reinforcement learning for reasoning","score":0.746999979019165},{"id":"https://openalex.org/keywords/tool-use","display_name":"tool use","score":0.3659999966621399},{"id":"https://openalex.org/keywords/embodied-agents","display_name":"embodied agents","score":0.9710000157356262},{"id":"https://openalex.org/keywords/search-agents","display_name":"search agents","score":0.875},{"id":"https://openalex.org/keywords/verifiable-rewards","display_name":"verifiable rewards","score":0.625},{"id":"https://openalex.org/keywords/multimodal-retrieval","display_name":"multimodal retrieval","score":0.5630000233650208},{"id":"https://openalex.org/keywords/multimodal-memory","display_name":"multimodal memory","score":0.6349999904632568},{"id":"https://openalex.org/keywords/canonical-correlation-analysis","display_name":"canonical correlation analysis","score":0.6859999895095825},{"id":"https://openalex.org/keywords/clip","display_name":"CLIP","score":0.9890000224113464},{"id":"https://openalex.org/keywords/siglip","display_name":"SigLIP","score":0.9700000286102295},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.8460000157356262},{"id":"https://openalex.org/keywords/agent-safety","display_name":"agent safety","score":0.5360000133514404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7095999717712402},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6934999823570251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5950000286102295},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.569599986076355},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5027999877929688},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.46149998903274536},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.44519999623298645},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.43140000104904175},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.4311999976634979},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3874000012874603},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35670000314712524},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3553999960422516},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C153874254","wikidata":"https://www.wikidata.org/wiki/Q115542","display_name":"Canonical correlation","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2944999933242798},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2913999855518341},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2662999927997589},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.20944/preprints202611.0215.v1","doi":"https://doi.org/10.20944/preprints202611.0215.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0215.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.20944/preprints202611.0215.v1","doi":"https://doi.org/10.20944/preprints202611.0215.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0215.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416271960","https://openalex.org/W7139934461","https://openalex.org/W7129568960","https://openalex.org/W4416097713","https://openalex.org/W7106209821","https://openalex.org/W4414973223","https://openalex.org/W7212959724","https://openalex.org/W7204106788","https://openalex.org/W7158880064","https://openalex.org/W7151838070"],"abstract_inverted_index":{"Multimodal":[0],"models":[1,29,53],"increasingly":[2],"reason":[3],"over":[4],"what":[5],"they":[6],"perceive,":[7],"act":[8],"in":[9,24,54,93,97,111],"digital":[10],"and":[11,14,60,67,70,80,88,106,132,143,150,156,174,178,181,195],"physical":[12],"environments,":[13],"retrieve":[15],"content":[16],"across":[17],"modalities.":[18],"This":[19],"survey":[20],"reviews":[21],"recent":[22],"advances":[23],"the":[25,187],"three":[26],"families":[27],"of":[28,41,57],"behind":[30],"these":[31],"abilities:":[32],"multimodal":[33,47,71],"reasoning":[34,59,122],"models,":[35,73],"which":[36,50,74,98],"reach":[37],"answers":[38],"through":[39],"chains":[40],"thought":[42],"trained":[43,146],"with":[44,62,134,147,183],"reinforcement":[45],"learning;":[46],"agentic":[48],"systems,":[49],"run":[51],"such":[52],"a":[55,83,104,107,112],"loop":[56],"perception,":[58],"action":[61],"tools,":[63],"graphical":[64],"interfaces,":[65],"robots":[66],"search":[68,144],"engines;":[69],"embedding":[72,116],"map":[75],"images,":[76],"text,":[77],"audio,":[78],"video":[79],"documents":[81],"into":[82],"shared":[84],"space":[85],"for":[86],"retrieval":[87],"memory.":[89],"We":[90],"present":[91],"them":[92],"one":[94],"mathematical":[95],"framework":[96],"every":[99],"model":[100],"composes":[101],"modality":[102],"encoders,":[103],"connector":[105],"foundation-model":[108],"backbone":[109],"ending":[110],"generative":[113],"or":[114],"an":[115],"head.":[117],"Within":[118],"it":[119],"we":[120,175],"trace":[121],"from":[123,137,152],"attention-based":[124],"visual":[125],"question":[126],"answering":[127],"to":[128,140,161],"group-relative":[129],"policy":[130],"optimization":[131],"``thinking":[133],"images'';":[135],"agents":[136,145],"tool-augmented":[138],"programs":[139],"GUI,":[141],"embodied":[142],"verifiable":[148],"rewards;":[149],"embeddings":[151],"canonical":[153],"correlation":[154],"analysis":[155],"contrastive":[157],"encoders":[158],"(CLIP,":[159],"SigLIP)":[160],"instruction-following":[162],"universal":[163],"embedders.":[164],"More":[165],"than":[166],"350":[167],"works":[168],"are":[169],"organized":[170],"along":[171],"five":[172],"taxonomies,":[173],"summarize":[176],"benchmarks":[177],"reported":[179],"results":[180],"close":[182],"open":[184],"problems,":[185],"including":[186],"perception":[188],"bottleneck,":[189],"faithful":[190],"reasoning,":[191],"agent":[192],"safety,":[193],"efficiency":[194],"evaluation.":[196]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}