{"id":"https://openalex.org/W7133354148","doi":"https://doi.org/10.48550/arxiv.2603.01050","title":"MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baseline","display_name":"MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baseline","publication_year":2026,"publication_date":"2026-03-01","ids":{"openalex":"https://openalex.org/W7133354148","doi":"https://doi.org/10.48550/arxiv.2603.01050"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.01050","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01050","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.01050","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127932717","display_name":"Huanjin Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Huanjin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107662000","display_name":"Qixiang Yin","orcid":"https://orcid.org/0009-0008-7515-1977"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Qixiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128011057","display_name":"Min Kyu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Min","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042424428","display_name":"Ziwang Zhao","orcid":"https://orcid.org/0000-0001-5538-3190"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Ziwang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127937364","display_name":"Yibo Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yibo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128023543","display_name":"Haotian Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Haotian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127963248","display_name":"Jingyi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jingyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127953535","display_name":"Jiaxing Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jiaxing","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":0.9067000150680542,"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":0.9067000150680542,"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":0.024700000882148743,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.007400000002235174,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/beam-search","display_name":"Beam search","score":0.5246999859809875},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.44510000944137573},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.41019999980926514},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.39890000224113464},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.36809998750686646},{"id":"https://openalex.org/keywords/visual-search","display_name":"Visual search","score":0.36390000581741333},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.35260000824928284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7703999876976013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5875999927520752},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5641999840736389},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.5246999859809875},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.36809998750686646},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C171089853","wikidata":"https://www.wikidata.org/wiki/Q7094123","display_name":"Online search","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3046000003814697},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C14838553","wikidata":"https://www.wikidata.org/wiki/Q7441639","display_name":"Search analytics","level":4,"score":0.288100004196167},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2718000113964081},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2676999866962433}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.01050","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01050","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:10.48550/arxiv.2603.01050","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01050","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"We":[0],"aim":[1],"to":[2,22,85,97,112,131],"develop":[3,176],"a":[4,67,178],"multimodal":[5,41,88,180],"research":[6,25,182],"agent":[7],"capable":[8],"of":[9,39,46,54],"explicit":[10],"reasoning":[11],"and":[12,16,50,74,77,81,116,184],"planning,":[13],"multi-tool":[14],"invocation,":[15],"cross-modal":[17],"information":[18],"synthesis,":[19],"enabling":[20,84,161],"it":[21],"conduct":[23],"deep":[24,181],"tasks.":[26],"However,":[27],"we":[28,63,100,151,175],"observe":[29],"three":[30,173],"main":[31],"challenges":[32],"in":[33],"developing":[34],"such":[35],"agents:":[36],"(1)":[37],"scarcity":[38],"search-intensive":[40,87],"QA":[42,69,89],"data,":[43],"(2)":[44],"lack":[45],"effective":[47],"search":[48,58,95,113,120,134,148,155,159,169],"trajectories,":[49],"(3)":[51],"prohibitive":[52],"cost":[53],"training":[55],"with":[56],"online":[57,168],"APIs.":[59,170],"To":[60],"tackle":[61],"them,":[62],"first":[64,104],"propose":[65],"Hyper-Search,":[66],"hypergraph-based":[68],"generation":[70],"method":[71],"that":[72,91,141],"models":[73],"connects":[75],"visual":[76],"textual":[78],"nodes":[79],"within":[80],"across":[82,190],"modalities,":[83],"generate":[86],"pairs":[90],"require":[92],"invoking":[93],"various":[94,147],"tools":[96],"solve.":[98],"Second,":[99],"introduce":[101],"DR-TTS,":[102],"which":[103],"decomposes":[105],"search-involved":[106],"tasks":[107,145],"into":[108],"several":[109],"categories":[110],"according":[111],"tool":[114,121,129],"types,":[115],"respectively":[117],"optimize":[118],"specialized":[119],"experts":[122,130],"for":[123],"each":[124],"tool.":[125],"It":[126],"then":[127],"recomposes":[128],"jointly":[132],"explore":[133],"trajectories":[135,140],"via":[136],"tree":[137],"search,":[138],"producing":[139],"successfully":[142],"solve":[143],"complex":[144],"using":[146,166],"tools.":[149],"Third,":[150],"build":[152],"an":[153],"offline":[154],"engine":[156],"supporting":[157],"multiple":[158],"tools,":[160],"agentic":[162],"reinforcement":[163],"learning":[164],"without":[165],"costly":[167],"With":[171],"the":[172],"designs,":[174],"MM-DeepResearch,":[177],"powerful":[179],"agent,":[183],"extensive":[185],"results":[186],"shows":[187],"its":[188],"superiority":[189],"benchmarks.":[191],"Code":[192],"is":[193],"available":[194],"at":[195],"https://github.com/HJYao00/MM-DeepResearch":[196]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-04T00:00:00"}