{"id":"https://openalex.org/W7204197867","doi":"https://doi.org/10.48550/arxiv.2608.21438","title":"DesignAgent3D: Interactive 3D Scene Editing via Designer-like Multimodal Reasoning","display_name":"DesignAgent3D: Interactive 3D Scene Editing via Designer-like Multimodal Reasoning","publication_year":2026,"publication_date":"2026-08-18","ids":{"openalex":"https://openalex.org/W7204197867","doi":"https://doi.org/10.48550/arxiv.2608.21438"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2608.21438","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21438","pdf_url":"https://arxiv.org/pdf/2608.21438","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.21438","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148151224","display_name":"Xiujin Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xiujin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148159878","display_name":"Tianyu Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Tianyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148064041","display_name":"Yilun Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yilun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5074757563","display_name":"Xiangliang Zhang","orcid":"https://orcid.org/0000-0001-6828-8563","observed_orcids":["https://orcid.org/0000-0001-6828-8563"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiangliang","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":0.9789999723434448,"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":0.9789999723434448,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.01119999960064888,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.003700000001117587,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/3d-scene-editing","display_name":"3D scene editing","score":0.9679999947547913},{"id":"https://openalex.org/keywords/multimodal-reasoning","display_name":"multimodal reasoning","score":0.7900000214576721},{"id":"https://openalex.org/keywords/agentic-framework","display_name":"agentic framework","score":0.6420000195503235},{"id":"https://openalex.org/keywords/spatial-grounding","display_name":"spatial grounding","score":0.6840000152587891},{"id":"https://openalex.org/keywords/object-localization","display_name":"object localization","score":0.8040000200271606},{"id":"https://openalex.org/keywords/neural-radiance-fields","display_name":"neural radiance fields","score":0.5960000157356262},{"id":"https://openalex.org/keywords/3d-gaussian-splatting","display_name":"3D Gaussian Splatting","score":0.9909999966621399},{"id":"https://openalex.org/keywords/novel-view-rendering","display_name":"novel view rendering","score":0.8730000257492065},{"id":"https://openalex.org/keywords/multi-view-consistency","display_name":"multi-view consistency","score":0.8519999980926514},{"id":"https://openalex.org/keywords/interactive-editing","display_name":"interactive editing","score":0.3779999911785126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8543999791145325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5692999958992004},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5636000037193298},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5536999702453613},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5485000014305115},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3864000141620636},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3747999966144562},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3727000057697296},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3025999963283539},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.2892000079154968},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.271699994802475},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C174252522","wikidata":"https://www.wikidata.org/wiki/Q3816772","display_name":"Natural language user interface","level":3,"score":0.26190000772476196},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.21438","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21438","pdf_url":"https://arxiv.org/pdf/2608.21438","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,"listed_in":[],"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.2608.21438","doi":"https://doi.org/10.48550/arxiv.2608.21438","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.21438","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,"listed_in":[],"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":"pmh:oai:arXiv.org:2608.21438","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.21438","pdf_url":"https://arxiv.org/pdf/2608.21438","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,"listed_in":[],"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"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text":[0],"guided":[1],"3D":[2,31,90,126,148,163],"scene":[3,91,138],"editing":[4,92],"provides":[5],"an":[6,83],"intuitive":[7],"interface":[8],"for":[9],"modifying":[10],"reconstructed":[11],"environments,":[12],"but":[13],"remains":[14],"difficult":[15],"because":[16],"natural":[17],"language":[18],"design":[19,110],"requests":[20],"are":[21,142],"often":[22],"semantically":[23],"underspecified":[24,109],"and":[25,70,128,152,162,183],"must":[26],"be":[27],"grounded":[28],"in":[29,124],"cluttered":[30],"scenes.":[32],"Existing":[33],"methods":[34],"typically":[35],"formulate":[36],"the":[37,71,105,116,125,146],"task":[38],"as":[39,93],"one-shot":[40],"conditional":[41],"generation":[42],"from":[43,61],"a":[44,94],"single":[45],"prompt,":[46],"failing":[47],"to":[48,107,119],"resolve":[49],"ambiguous":[50],"user":[51,106],"intents":[52],"or":[53,122],"achieve":[54],"precise":[55],"spatial":[56,180],"grounding.":[57],"Consequently,":[58],"they":[59],"suffer":[60],"severe":[62],"object":[63],"localization":[64,181],"drift,":[65],"tracking":[66],"failure":[67],"under":[68],"occlusions,":[69],"notorious":[72],"multi-view":[73,153,185],"\"sticker":[74],"effect.\"":[75],"To":[76],"overcome":[77],"these":[78],"limitations,":[79],"we":[80],"present":[81],"DesignAgent3D,":[82],"interactive":[84],"multimodal":[85],"agentic":[86],"framework":[87],"that":[88,168],"reformulates":[89],"designer-like":[95],"Plan-Perceive-Act":[96],"paradigm.":[97],"The":[98,140],"agent":[99],"first":[100],"plans":[101],"by":[102,114,131],"interacting":[103],"with":[104],"clarify":[108],"goals,":[111],"then":[112],"perceives":[113],"grounding":[115],"intended":[117],"edit":[118],"specific":[120],"objects":[121],"regions":[123],"scene,":[127],"finally":[129],"acts":[130],"applying":[132],"controlled":[133],"visual":[134],"modifications":[135],"while":[136],"preserving":[137],"consistency.":[139,186],"edits":[141],"further":[143],"integrated":[144],"into":[145],"underlying":[147],"representation,":[149],"supporting":[150],"persistent":[151],"consistent":[154],"novel-view":[155],"rendering.":[156],"Extensive":[157],"experiments":[158],"across":[159],"both":[160],"NeRF":[161],"Gaussian":[164],"Splatting":[165],"backbones":[166],"demonstrate":[167],"DesignAgent3D":[169],"significantly":[170],"outperforms":[171],"state-of-the-art":[172],"baselines,":[173],"delivering":[174],"superior":[175],"semantic":[176],"intent":[177],"alignment,":[178],"impeccable":[179],"accuracy,":[182],"high-fidelity":[184]},"counts_by_year":[],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2026-08-26T00:00:00"}