{"id":"https://openalex.org/W7155053861","doi":"https://doi.org/10.48550/arxiv.2604.16729","title":"Agentic Large Language Models for Training-Free Neuro-Radiological Image Analysis","display_name":"Agentic Large Language Models for Training-Free Neuro-Radiological Image Analysis","publication_year":2026,"publication_date":"2026-04-17","ids":{"openalex":"https://openalex.org/W7155053861","doi":"https://doi.org/10.48550/arxiv.2604.16729"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.16729","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16729","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2604.16729","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041700318","display_name":"Ayhan Can Erdur","orcid":"https://orcid.org/0009-0006-0290-0434"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erdur, Ayhan Can","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050034758","display_name":"Daniel Scholz","orcid":"https://orcid.org/0000-0002-9310-0101"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Scholz, Daniel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134202189","display_name":"Jiazhen Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Jiazhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134123594","display_name":"Benedikt Wiestler","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wiestler, Benedikt","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134175931","display_name":"Daniel Rueckert","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rueckert, Daniel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073740173","display_name":"Jan C. Peeken","orcid":"https://orcid.org/0000-0003-2679-9853"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peeken, Jan C.","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":0.7901999950408936,"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":0.7901999950408936,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.058400001376867294,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.020400000736117363,"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/leverage","display_name":"Leverage (statistics)","score":0.6560999751091003},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5587000250816345},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5360999703407288},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5181000232696533},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.47130000591278076},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.37439998984336853},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.3546000123023987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6934999823570251},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6560999751091003},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5587000250816345},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5360999703407288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5228000283241272},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5181000232696533},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.47130000591278076},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44440001249313354},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.37439998984336853},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3564999997615814},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.33090001344680786},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2896000146865845},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2624000012874603},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.16729","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16729","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.16729","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16729","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"State-of-the-art":[0],"large":[1],"language":[2],"models":[3,160],"(LLMs)":[4],"show":[5],"high":[6],"performance":[7],"in":[8,70],"general":[9],"visual":[10],"question":[11],"answering.":[12],"However,":[13],"a":[14,43,82,178],"fundamental":[15],"limitation":[16],"remains:":[17],"current":[18],"architectures":[19],"lack":[20],"the":[21,47,64,152,206],"native":[22],"3D":[23,51],"spatial":[24],"reasoning":[25],"required":[26],"for":[27,49,86,208],"direct":[28],"analysis":[29,200],"of":[30,66,154,170,181],"volumetric":[31,126,141],"medical":[32],"imaging,":[33],"such":[34,67],"as":[35],"CT":[36],"or":[37,210],"MRI.":[38],"Emerging":[39],"agentic":[40,68,84,172,193],"AI":[41,194],"offers":[42],"new":[44],"solution,":[45],"eliminating":[46],"need":[48,207],"intrinsic":[50],"processing":[52],"by":[53,157],"enabling":[54],"LLMs":[55,96],"to":[56,143,166],"orchestrate":[57],"and":[58,125,140,176],"leverage":[59],"specialized":[60],"external":[61],"tools.":[62],"Yet,":[63],"feasibility":[65],"frameworks":[69],"complex,":[71],"multi-step":[72],"radiological":[73,135],"workflows":[74],"remains":[75],"underexplored.":[76],"In":[77],"this":[78],"work,":[79],"we":[80,174],"present":[81],"training-free":[83],"pipeline":[85],"automated":[87],"brain":[88],"MRI":[89],"analysis.":[90,127],"Validating":[91],"our":[92,108,130],"methodology":[93],"on":[94],"several":[95],"(GPT-5.1,":[97],"Gemini":[98],"3":[99],"Pro,":[100],"Claude":[101],"Sonnet":[102],"4.5)":[103],"with":[104],"off-the-shelf":[105],"domain-specific":[106],"tools,":[107],"system":[109],"autonomously":[110],"executes":[111],"complex":[112,134],"end-to-end":[113],"workflows,":[114],"including":[115],"preprocessing":[116],"(skull":[117],"stripping,":[118],"registration),":[119],"pathology":[120],"segmentation":[121,139],"(glioma,":[122],"meningioma,":[123],"metastases),":[124],"We":[128,150],"evaluate":[129],"framework":[131],"across":[132],"increasingly":[133],"tasks,":[136],"from":[137,185],"single-scan":[138],"reporting":[142],"longitudinal":[144],"response":[145],"assessment":[146],"requiring":[147],"multi-timepoint":[148],"comparisons.":[149],"analyze":[151],"impact":[153],"architectural":[155],"design":[156],"comparing":[158],"single-agent":[159],"against":[161],"multi-agent":[162],"\"domain-expert\"":[163],"collaborations.":[164],"Finally,":[165],"support":[167],"rigorous":[168],"evaluation":[169],"future":[171],"systems,":[173],"introduce":[175],"release":[177],"benchmark":[179],"dataset":[180],"image-prompt-answer":[182],"tuples":[183],"derived":[184],"public":[186],"BraTS":[187],"data.":[188],"Our":[189],"results":[190],"demonstrate":[191],"that":[192],"can":[195],"solve":[196],"highly":[197],"neuro-radiological":[198],"image":[199],"tasks":[201],"through":[202],"tool":[203],"use":[204],"without":[205],"training":[209],"fine-tuning.":[211]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-22T00:00:00"}