{"id":"https://openalex.org/W7138970705","doi":"https://doi.org/10.48550/arxiv.2603.16967","title":"MSRAMIE: Multimodal Structured Reasoning Agent for Multi-instruction Image Editing","display_name":"MSRAMIE: Multimodal Structured Reasoning Agent for Multi-instruction Image Editing","publication_year":2026,"publication_date":"2026-03-17","ids":{"openalex":"https://openalex.org/W7138970705","doi":"https://doi.org/10.48550/arxiv.2603.16967"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.16967","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16967","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":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.2603.16967","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130135342","display_name":"Zhaoyuan Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Zhaoyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130128497","display_name":"Ken Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Ken","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101688508","display_name":"Xiangwei Wang","orcid":"https://orcid.org/0009-0001-3649-0852"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiangwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130009805","display_name":"Yu Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044517527","display_name":"Sachith Seneviratne","orcid":"https://orcid.org/0000-0001-9094-2736"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seneviratne, Sachith","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067418792","display_name":"Saman Halgamuge","orcid":"https://orcid.org/0000-0002-2536-4930"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Halgamuge, Saman","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":0.3377000093460083,"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":0.3377000093460083,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1664000004529953,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.05460000038146973,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.6414999961853027},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5073999762535095},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4830999970436096},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.41609999537467957},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.38760000467300415},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.38370001316070557},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.367900013923645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8270999789237976},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6414999961853027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5295000076293945},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5073999762535095},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4830999970436096},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.41609999537467957},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3869999945163727},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3506999909877777},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C185874996","wikidata":"https://www.wikidata.org/wiki/Q269699","display_name":"Interdependence","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3010999858379364},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.16967","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16967","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.16967","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.16967","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.443798303604126}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"instruction-based":[1],"image":[2,92,134],"editing":[3,69,93,115,135],"models":[4,70],"perform":[5],"well":[6],"with":[7,32],"simple,":[8],"single-step":[9],"instructions":[10,110],"but":[11],"degrade":[12],"in":[13,176],"realistic":[14],"scenarios":[15],"that":[16,100,155],"involve":[17],"multiple,":[18],"lengthy,":[19],"and":[20,44,74,90,105,124,137,149,168,186],"interdependent":[21],"directives.":[22],"A":[23],"main":[24],"cause":[25],"is":[26,38],"the":[27,102,133,157,170],"scarcity":[28],"of":[29,132,172],"training":[30],"data":[31,43],"complex":[33,109],"multi-instruction":[34,76],"annotations.":[35],"However,":[36],"it":[37],"costly":[39],"to":[40],"collect":[41],"such":[42],"retrain":[45],"these":[46],"models.":[47],"To":[48],"address":[49],"this":[50],"challenge,":[51],"we":[52],"propose":[53],"MSRAMIE,":[54],"a":[55,96,177],"training-free":[56],"agent":[57],"framework":[58],"built":[59],"on":[60],"Multimodal":[61],"Large":[62],"Language":[63],"Model":[64],"(MLLM).":[65],"MSRAMIE":[66,161],"takes":[67],"existing":[68],"as":[71,156],"plug-in":[72],"components":[73],"handle":[75],"tasks":[77],"via":[78],"structured":[79],"multimodal":[80],"reasoning.":[81],"It":[82],"orchestrates":[83],"iterative":[84],"interactions":[85],"between":[86],"an":[87,91],"MLLM-based":[88],"Instructor":[89],"Actor,":[94],"introducing":[95],"novel":[97],"reasoning":[98],"topology":[99,145],"comprises":[101],"proposed":[103],"Tree-of-States":[104],"Graph-of-References.":[106],"During":[107],"inference,":[108],"are":[111],"decomposed":[112],"into":[113],"multiple":[114],"steps":[116],"which":[117,128],"enable":[118],"state":[119],"transitions,":[120],"cross-step":[121],"information":[122],"aggregation,":[123],"original":[125],"input":[126],"recall,":[127],"enables":[129],"systematic":[130],"exploration":[131],"space":[136],"flexible":[138],"progressive":[139],"output":[140],"refinement.":[141],"The":[142],"visualizable":[143],"inference":[144],"further":[146],"provides":[147],"interpretable":[148],"controllable":[150],"decision":[151],"pathways.":[152],"Experiments":[153],"show":[154],"instruction":[158,164],"complexity":[159],"increases,":[160],"can":[162],"improve":[163],"following":[165],"over":[166,180],"15%":[167],"increases":[169],"probability":[171],"finishing":[173],"all":[174],"modifications":[175],"single":[178],"run":[179],"100%,":[181],"while":[182],"preserving":[183],"perceptual":[184],"quality":[185],"maintaining":[187],"visual":[188],"consistency.":[189]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-20T00:00:00"}