{"id":"https://openalex.org/W4416246765","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1439","title":"DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile Phone Agents","display_name":"DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile Phone Agents","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416246765","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1439"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1439","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1439","pdf_url":"https://aclanthology.org/2026.findings-acl.1439.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1439.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kai Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Shi","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101646225","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0002-1646-3910"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Yang","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000841815","display_name":"Yang Ni","orcid":"https://orcid.org/0000-0002-3472-386X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ni Yang","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107827384","display_name":"B. Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Binqiang Pan","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066624863","display_name":"Qingsong Xie","orcid":"https://orcid.org/0000-0001-6974-2019"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingsong Xie","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100766256","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0001-7313-6361"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhangchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433323","display_name":"Zhenyu Yang","orcid":"https://orcid.org/0000-0002-0773-0298"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenyu Yang","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112471534","display_name":"Tao Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianhuang Su","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007720098","display_name":"H. Lu","orcid":"https://orcid.org/0000-0001-6332-2785"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haonan Lu","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]}],"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":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00690608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28813","last_page":"28830"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.10429999977350235,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.10429999977350235,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13194","display_name":"ICT in Developing Communities","score":0.05990000069141388,"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"}},{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.039400000125169754,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6872000098228455},{"id":"https://openalex.org/keywords/mobile-phone","display_name":"Mobile phone","score":0.6517999768257141},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6236000061035156},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5353999733924866},{"id":"https://openalex.org/keywords/cellular-network","display_name":"Cellular network","score":0.40310001373291016},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3887999951839447},{"id":"https://openalex.org/keywords/mobile-telephony","display_name":"Mobile telephony","score":0.36419999599456787},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.33410000801086426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778000235557556},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6872000098228455},{"id":"https://openalex.org/C2777421447","wikidata":"https://www.wikidata.org/wiki/Q17517","display_name":"Mobile phone","level":2,"score":0.6517999768257141},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6236000061035156},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5353999733924866},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4876999855041504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41920000314712524},{"id":"https://openalex.org/C153646914","wikidata":"https://www.wikidata.org/wiki/Q535695","display_name":"Cellular network","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3887999951839447},{"id":"https://openalex.org/C95491727","wikidata":"https://www.wikidata.org/wiki/Q992968","display_name":"Mobile telephony","level":3,"score":0.36419999599456787},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33410000801086426},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2962999939918518},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.26019999384880066}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1439","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1439","pdf_url":"https://aclanthology.org/2026.findings-acl.1439.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.19336","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.19336","pdf_url":"https://arxiv.org/pdf/2510.19336","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.2510.19336","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.19336","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.findings-acl.1439","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1439","pdf_url":"https://aclanthology.org/2026.findings-acl.1439.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416246765.pdf","grobid_xml":"https://content.openalex.org/works/W4416246765.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Mobile":[0],"Phone":[1],"Agents":[2],"(MPAs)":[3],"have":[4],"emerged":[5],"as":[6,25],"a":[7,75],"promising":[8],"research":[9],"direction":[10],"due":[11],"to":[12,54,103,157,207],"their":[13,30],"broad":[14],"applicability":[15],"across":[16],"diverse":[17,116],"scenarios.While":[18],"Multimodal":[19],"Large":[20],"Language":[21],"Models":[22],"(MLLMs)":[23],"serve":[24],"the":[26,99,181,195],"foundation":[27],"for":[28,48,60,88,191],"MPAs,":[29],"effectiveness":[31,204],"in":[32,126,174],"handling":[33],"multiple":[34],"mobile":[35,108,119],"phone":[36,109],"tasks":[37],"simultaneously":[38],"remains":[39],"limited.Although":[40],"multitask":[41,49],"supervised":[42],"fine-tuning":[43],"(SFT)":[44],"is":[45],"widely":[46],"adopted":[47],"learning,":[50],"existing":[51],"approaches":[52,171],"struggle":[53],"determine":[55],"optimal":[56,80,133,161],"training":[57],"data":[58,81,134,162],"compositions":[59],"peak":[61],"performance.To":[62],"address":[63],"this":[64],"challenge,":[65],"we":[66,96],"propose":[67],"DaMo":[68,130,139,168,179,198],"(Data":[69],"Mixture":[70],"Optimizer)a":[71],"novel":[72],"solution":[73],"employing":[74],"trainable":[76],"network":[77],"that":[78],"predicts":[79],"mixtures":[82],"by":[83,172,183],"forecasting":[84],"downstream":[85],"task":[86],"performance":[87],"any":[89],"given":[90],"dataset":[91],"ratio.To":[92],"support":[93],"comprehensive":[94],"evaluation,":[95],"introduce":[97],"PhoneAgent-Bench,":[98],"first":[100],"specialized":[101],"benchmark":[102],"evaluate":[104],"MLLMs":[105],"on":[106,145,165,194],"multimodal":[107],"tasks,":[110],"comprising":[111],"1,235":[112],"QA":[113],"pairs":[114],"spanning":[115],"real-world":[117],"industrial":[118],"application":[120],"scenarios.Demonstrating":[121],"strong":[122],"predictive":[123],"capability":[124],"(R\u00b2=0.81)":[125],"small-scale":[127],"pilot":[128],"experiments,":[129],"efficiently":[131],"extrapolates":[132],"mixing":[135],"configurations.Our":[136],"results":[137],"show":[138],"achieves":[140],"3.06%":[141],"average":[142,177],"score":[143],"improvement":[144],"PhoneAgentBench":[146],"and":[147,154],"open-source":[148,166],"benchmarks,":[149,167],"including":[150],"BFCL-v3,":[151],"MME-Reasoning,":[152],"MME-Perception,":[153],"OCRBench,":[155],"compared":[156],"alternative":[158],"methods.Through":[159],"predicting":[160],"mixture":[163],"only":[164],"outperforms":[169],"other":[170,186,208],"6.70%":[173],"terms":[175],"of":[176],"score.Moreover,":[178],"improves":[180],"metrics":[182],"12.74%":[184],"than":[185],"methods":[187],"when":[188,205],"used":[189],"solely":[190],"MLLM":[192],"optimization":[193],"BFCL-v3":[196],"task.Notably,":[197],"maintains":[199],"robust":[200],"scalability,":[201],"preserving":[202],"its":[203],"applied":[206],"model":[209],"architectures.":[210]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-24T00:00:00"}