{"id":"https://openalex.org/W7164575830","doi":"https://doi.org/10.48550/arxiv.2606.13368","title":"IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing","display_name":"IterCAD: An Iterative Multimodal Agent for Visually-Grounded CAD Generation and Editing","publication_year":2026,"publication_date":"2026-06-11","ids":{"openalex":"https://openalex.org/W7164575830","doi":"https://doi.org/10.48550/arxiv.2606.13368"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.13368","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.13368","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.2606.13368","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138540549","display_name":"Tao Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138535939","display_name":"Jiaxin Ai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ai, Jiaxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056126166","display_name":"Licheng Wen","orcid":"https://orcid.org/0000-0003-2707-3165"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen, Licheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138524717","display_name":"Xueheng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xueheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101292475","display_name":"Shu Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, Shu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138550142","display_name":"Siqi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Siqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004152079","display_name":"Nianchen Deng","orcid":"https://orcid.org/0000-0002-5292-266X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Nianchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138515991","display_name":"Xinyu Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Xinyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102934648","display_name":"Hongbin Zhou","orcid":"https://orcid.org/0000-0002-7133-8987"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Hongbin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121562798","display_name":"Pinlong Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Pinlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121592360","display_name":"Daocheng Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Daocheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138496189","display_name":"Yu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138491354","display_name":"Hairong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hairong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138546690","display_name":"Botian Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Botian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101138291","display_name":"Xuemeng Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xuemeng","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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.26579999923706055,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.26579999923706055,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11159","display_name":"Manufacturing Process and Optimization","score":0.19099999964237213,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10789","display_name":"Interactive and Immersive Displays","score":0.13099999725818634,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/executable","display_name":"Executable","score":0.7394000291824341},{"id":"https://openalex.org/keywords/cad","display_name":"CAD","score":0.6832000017166138},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5759000182151794},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.535099983215332},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.524399995803833},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42739999294281006},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.41280001401901245},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.39959999918937683},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3806000053882599},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.3765999972820282}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742000222206116},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.7394000291824341},{"id":"https://openalex.org/C194789388","wikidata":"https://www.wikidata.org/wiki/Q17855283","display_name":"CAD","level":2,"score":0.6832000017166138},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5759000182151794},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.524399995803833},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42739999294281006},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.41280001401901245},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36410000920295715},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.33489999175071716},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3255999982357025},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C119823426","wikidata":"https://www.wikidata.org/wiki/Q184793","display_name":"Computer Aided Design","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C207850805","wikidata":"https://www.wikidata.org/wiki/Q269608","display_name":"Reverse engineering","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3091999888420105},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C106246047","wikidata":"https://www.wikidata.org/wiki/Q4928435","display_name":"Iterative design","level":3,"score":0.2915000021457672},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C10272871","wikidata":"https://www.wikidata.org/wiki/Q929972","display_name":"Software inspection","level":5,"score":0.29030001163482666},{"id":"https://openalex.org/C2776313386","wikidata":"https://www.wikidata.org/wiki/Q18018756","display_name":"Chamfer (geometry)","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.2720000147819519},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.257099986076355},{"id":"https://openalex.org/C34972735","wikidata":"https://www.wikidata.org/wiki/Q2920267","display_name":"Engineering design process","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.251800000667572},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.13368","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.13368","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.2606.13368","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.13368","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":"Industry, innovation and infrastructure","score":0.6143205165863037,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Computer-Aided":[0],"Design":[1],"is":[2],"pivotal":[3],"in":[4,162,173],"modern":[5],"manufacturing,":[6],"yet":[7],"existing":[8,160],"automated":[9],"methods":[10],"predominantly":[11],"rely":[12],"on":[13],"open-loop,":[14],"one-shot":[15],"generation,":[16],"creating":[17],"a":[18,30,47,51,72,136],"mismatch":[19],"with":[20,106],"iterative":[21,175],"real-world":[22],"practices.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27,70,117],"present":[28],"IterCAD,":[29],"unified":[31],"multimodal":[32,52],"agent":[33,53,97],"framework":[34],"for":[35],"closed-loop,":[36],"interactive":[37],"CAD":[38,57],"generation":[39],"and":[40,54,64,90,113,123,143,166],"editing.":[41],"We":[42,94],"formulate":[43],"the":[44,96,119,125],"task":[45],"as":[46],"multi-turn":[48],"interaction":[49,92],"between":[50],"an":[55],"executable":[56],"sandbox,":[58],"covering":[59],"three":[60],"tasks:":[61],"Drawing-to-Code,":[62],"Text-to-Code,":[63],"Interactive":[65],"Editing.":[66],"To":[67],"support":[68],"this,":[69],"develop":[71],"data":[73],"synthesis":[74],"pipeline":[75],"incorporating":[76],"advanced":[77],"industrial":[78],"manufacturing":[79],"features":[80],"to":[81,109],"generate":[82],"standard-compliant":[83],"multi-view":[84],"engineering":[85],"drawings,":[86],"complex":[87],"code-editing":[88],"tasks,":[89],"high-fidelity":[91],"trajectories.":[93],"optimize":[95],"via":[98],"progressive":[99],"SFT":[100],"followed":[101],"by":[102],"geometry-aware":[103],"reinforcement":[104],"learning":[105],"viable-prefix":[107],"masking":[108],"enhance":[110],"code":[111,141,164],"executability":[112,165],"geometric":[114,144,167],"fidelity.":[115],"Finally,":[116],"introduce":[118],"IterCAD-Bench":[120],"evaluation":[121],"suite":[122],"propose":[124],"Chamfer":[126],"Distance":[127],"Tolerance-Recall":[128],"(CD-TR)":[129],"curve":[130],"alongside":[131],"its":[132],"AUC-TR":[133],"metric,":[134],"establishing":[135],"survivor-bias-free":[137],"standard":[138],"that":[139,149],"unifies":[140],"validity":[142],"precision.":[145],"Extensive":[146],"experiments":[147],"demonstrate":[148],"IterCAD":[150],"achieves":[151],"highly":[152],"competitive":[153],"performance":[154],"across":[155],"multiple":[156],"benchmarks,":[157],"significantly":[158],"outperforming":[159],"approaches":[161],"both":[163],"precision,":[168],"while":[169],"exhibiting":[170],"superior":[171],"capabilities":[172],"closed-loop":[174],"refinement.":[176]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-13T00:00:00"}
