{"id":"https://openalex.org/W4414990013","doi":"https://doi.org/10.18653/v1/2026.acl-long.114","title":"MMSearch-R1: Incentivizing LMMs to Search","display_name":"MMSearch-R1: Incentivizing LMMs to Search","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414990013","doi":"https://doi.org/10.18653/v1/2026.acl-long.114"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.114","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.114","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.18653/v1/2026.acl-long.114","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103265617","display_name":"Jinming Wu","orcid":"https://orcid.org/0009-0001-1824-0809"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinming Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zihao Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihao Deng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318137","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-2295-2542"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101677604","display_name":"Yiding Liu","orcid":"https://orcid.org/0000-0003-0540-9289"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiding Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101603892","display_name":"Bo You","orcid":"https://orcid.org/0000-0001-8702-3077"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo You","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374364","display_name":"Bo Li","orcid":"https://orcid.org/0000-0001-7500-8355"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101108160","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun MA","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100406050","display_name":"Ziwei Liu","orcid":"https://orcid.org/0000-0002-4220-5958"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziwei Liu","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01114456,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2456","last_page":"2487"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.828000009059906,"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/T11269","display_name":"Algorithms and Data Compression","score":0.828000009059906,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.7828999757766724,"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/T11567","display_name":"semigroups and automata theory","score":0.7282000184059143,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.6003999710083008},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.510699987411499},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4772999882698059},{"id":"https://openalex.org/keywords/visual-search","display_name":"Visual search","score":0.44839999079704285},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4327999949455261},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.42410001158714294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7106000185012817},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6003999710083008},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5932000279426575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5600000023841858},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.510699987411499},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4772999882698059},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.44839999079704285},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4327999949455261},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.32100000977516174},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27649998664855957}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.114","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.114","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.20670","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.20670","pdf_url":"https://arxiv.org/pdf/2506.20670","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.20670","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.20670","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:10.18653/v1/2026.acl-long.114","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.114","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Robust":[0],"deployment":[1],"of":[2,22,160,170],"large":[3],"multimodal":[4,106,196],"models":[5],"(LMMs)":[6],"in":[7,66,195],"real-world":[8,23,67],"scenarios":[9],"requires":[10],"access":[11],"to":[12,43,61,82,88,188],"external":[13],"knowledge":[14,120],"sources,":[15],"given":[16],"the":[17,52,80,161,168],"complexity":[18],"and":[19,32,75,86,118,122,130,139,147],"dynamic":[20],"nature":[21],"information.":[24],"Existing":[25],"approaches":[26],"such":[27],"as":[28],"retrieval-augmented":[29],"generation":[30],"(RAG)":[31],"prompt":[33],"engineered":[34],"search":[35,47,65,77,98,107,141,177],"agents":[36],"rely":[37],"on":[38,145],"rigid":[39],"pipelines,":[40],"often":[41],"leading":[42],"inefficient":[44],"or":[45],"excessive":[46],"behaviors.":[48],"We":[49,103,182],"present":[50],"MMSearch-R1,":[51],"first":[53],"end-to-end":[54],"reinforcement":[55],"learning":[56],"framework":[57,71],"that":[58,114,152],"enables":[59],"LMMs":[60],"perform":[62],"on-demand,":[63],"multi-turn":[64],"Internet":[68],"environments.":[69],"Our":[70],"integrates":[72],"both":[73,128],"image":[74],"text":[76],"tools,":[78],"allowing":[79],"model":[81,154,163,174],"reason":[83],"about":[84],"when":[85],"how":[87],"invoke":[89],"them":[90],"guided":[91],"by":[92,179],"an":[93],"outcome-based":[94],"reward":[95],"with":[96,127],"a":[97,105,111,124,171],"penalty.":[99],"To":[100],"support":[101],"training,":[102],"collect":[104],"VQA":[108,149],"dataset":[109],"through":[110],"semi-automated":[112],"pipeline":[113],"covers":[115],"diverse":[116],"visual":[117],"textual":[119],"needs":[121],"curate":[123],"search-balanced":[125],"subset":[126],"search-required":[129],"search-free":[131],"samples,":[132],"which":[133],"proves":[134],"essential":[135],"for":[136,192],"shaping":[137],"efficient":[138],"on-demand":[140],"behavior.":[142],"Extensive":[143],"experiments":[144],"knowledge-intensive":[146],"info-seeking":[148],"tasks":[150],"show":[151],"our":[153],"not":[155],"only":[156],"outperforms":[157],"RAG-based":[158,173],"baselines":[159],"same":[162],"size,":[164],"but":[165],"also":[166],"matches":[167],"performance":[169],"larger":[172],"while":[175],"reducing":[176],"calls":[178],"over":[180],"30%.":[181],"further":[183],"analyze":[184],"key":[185],"empirical":[186],"findings":[187],"offer":[189],"actionable":[190],"insights":[191],"advancing":[193],"research":[194],"search.":[197]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-09T00:00:00"}