{"id":"https://openalex.org/W7134287408","doi":"https://doi.org/10.48550/arxiv.2603.05551","title":"AutothinkRAG: Complexity-Aware Control of Retrieval-Augmented Reasoning for Image-Text Interaction","display_name":"AutothinkRAG: Complexity-Aware Control of Retrieval-Augmented Reasoning for Image-Text Interaction","publication_year":2026,"publication_date":"2026-03-05","ids":{"openalex":"https://openalex.org/W7134287408","doi":"https://doi.org/10.48550/arxiv.2603.05551"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.05551","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128614066","display_name":"Jiashu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jiashu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128460976","display_name":"Zhang, Chi, Ph. D. Massachusetts Institute of Technology, Department of Chemistry","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023291127","display_name":"Abudukelimu Wuerkaixi","orcid":"https://orcid.org/0000-0002-5609-606X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wuerkaixi, Abudukelimu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128561547","display_name":"Xuxin Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Xuxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128403607","display_name":"Cao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128444224","display_name":"Ke Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Ke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128561562","display_name":"Xu Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128552431","display_name":"Xunliang Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Xunliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"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":0.9940000176429749,"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":0.9940000176429749,"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/T10028","display_name":"Topic Modeling","score":0.0013000000035390258,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0007999999797903001,"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/inference","display_name":"Inference","score":0.6080999970436096},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.446399986743927},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4154999852180481},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.382999986410141},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.34880000352859497},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.33559998869895935},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.3124000132083893},{"id":"https://openalex.org/keywords/workcell","display_name":"Workcell","score":0.3109000027179718},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3100000023841858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8072999715805054},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6080999970436096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4975999891757965},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.446399986743927},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3391000032424927},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C2781411174","wikidata":"https://www.wikidata.org/wiki/Q8034662","display_name":"Workcell","level":3,"score":0.3109000027179718},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30059999227523804},{"id":"https://openalex.org/C122783720","wikidata":"https://www.wikidata.org/wiki/Q183065","display_name":"Interpreter","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C44210515","wikidata":"https://www.wikidata.org/wiki/Q16968978","display_name":"Bespoke","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2590000033378601},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.2574999928474426},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C15569618","wikidata":"https://www.wikidata.org/wiki/Q3561421","display_name":"Liveness","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.05551","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.05551","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.05551","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":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2603.05551","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"score":0.5343502759933472,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"document":[1,64],"question":[2],"answering":[3],"requires":[4],"retrieving":[5],"dispersed":[6],"evidence":[7],"from":[8],"visually":[9],"rich":[10],"long":[11],"documents":[12],"and":[13,35,51,79,85,88,122,130,135,141,148,160,180],"performing":[14],"reliable":[15],"reasoning":[16,86,121],"over":[17],"heterogeneous":[18],"information.":[19],"Existing":[20],"multimodal":[21,63],"RAG":[22],"systems":[23],"remain":[24],"limited":[25],"by":[26,158,163],"two":[27,68],"bottlenecks:":[28],"static":[29],"retrieval":[30,84,179],"that":[31,40,75,94,144,168],"ignores":[32],"query":[33,77],"complexity,":[34],"end-to-end":[36],"Vision-Language":[37],"Models":[38],"(VLMs)":[39],"couple":[41],"visual":[42,102,107],"perception":[43],"with":[44],"logical":[45,120],"reasoning,":[46],"leading":[47],"to":[48,81,104,116],"inefficient":[49],"computation":[50],"unstable":[52],"answer":[53,123],"generation.":[54],"We":[55],"propose":[56],"AutoThinkRAG,":[57],"a":[58,71,90,96,100],"complexity-aware":[59],"inference":[60],"architecture":[61,93],"for":[62,119],"QA.":[65],"It":[66],"has":[67],"components:":[69],"(1)":[70],"Query":[72],"Complexity":[73],"Router":[74],"analyzes":[76],"difficulty":[78],"structure":[80],"adaptively":[82],"select":[83],"paths;":[87],"(2)":[89],"Perception--Reasoning":[91],"Decoupling":[92],"uses":[95],"lightweight":[97],"VLM":[98],"as":[99],"high-fidelity":[101],"interpreter":[103],"convert":[105],"query-relevant":[106],"cues":[108],"into":[109],"textual":[110],"representations,":[111],"which":[112],"are":[113,171],"then":[114],"passed":[115],"an":[117],"LLM":[118],"synthesis.":[124],"This":[125],"design":[126],"improves":[127],"both":[128],"efficiency":[129],"robustness,":[131],"especially":[132],"on":[133,139,174],"long-document":[134],"unanswerable":[136],"queries.":[137],"Experiments":[138],"DocBench":[140],"MMLongBench":[142],"show":[143,167],"AutoThinkRAG":[145],"achieves":[146],"82.13\\%":[147],"51.29\\%":[149],"overall":[150],"accuracy,":[151],"respectively,":[152],"while":[153],"reducing":[154],"per-query":[155],"token":[156],"consumption":[157],"18.9\\%":[159],"monetary":[161],"cost":[162],"18.2\\%.":[164],"Further":[165],"analyses":[166],"the":[169],"gains":[170],"most":[172],"pronounced":[173],"complex":[175],"queries":[176],"requiring":[177],"adaptive":[178],"multi-step":[181],"reasoning.":[182]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-10T00:00:00"}