{"id":"https://openalex.org/W7202006105","doi":"https://doi.org/10.48550/arxiv.2608.06161","title":"iARCS: Iterative Agentic RL for Controllable 3D Scene Generation","display_name":"iARCS: Iterative Agentic RL for Controllable 3D Scene Generation","publication_year":2026,"publication_date":"2026-08-06","ids":{"openalex":"https://openalex.org/W7202006105","doi":"https://doi.org/10.48550/arxiv.2608.06161"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.06161","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.06161","pdf_url":"https://arxiv.org/pdf/2608.06161","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/2608.06161","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062626843","display_name":"Saugat Adhikari","orcid":"https://orcid.org/0000-0002-7846-2200","observed_orcids":["https://orcid.org/0000-0002-7846-2200"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adhikari, Saugat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146087496","display_name":"Ashok Prasad Neupane","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Neupane, Ashok Prasad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114474734","display_name":"Pramish Paudel","orcid":"https://orcid.org/0009-0006-3145-5077","observed_orcids":["https://orcid.org/0009-0006-3145-5077"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paudel, Pramish","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009256545","display_name":"Ajad Chhatkuli","orcid":"https://orcid.org/0000-0003-2051-2209","observed_orcids":["https://orcid.org/0000-0003-2051-2209"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chhatkuli, Ajad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050696776","display_name":"Danda Pani Paudel","orcid":"https://orcid.org/0000-0002-1739-1867","observed_orcids":["https://orcid.org/0000-0002-1739-1867"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paudel, Danda Pani","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.39719998836517334,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.39719998836517334,"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"}},{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.2720000147819519,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.10610000044107437,"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/3d-scene-generation","display_name":"3D scene generation","score":0.9570000171661377},{"id":"https://openalex.org/keywords/agentic-reinforcement-learning","display_name":"agentic reinforcement learning","score":0.9089999794960022},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"synthetic data","score":0.5059999823570251},{"id":"https://openalex.org/keywords/walkability","display_name":"walkability","score":0.5910000205039978},{"id":"https://openalex.org/keywords/reachability","display_name":"reachability","score":0.9350000023841858},{"id":"https://openalex.org/keywords/physical-plausibility","display_name":"physical plausibility","score":0.718999981880188},{"id":"https://openalex.org/keywords/scene-layout","display_name":"scene layout","score":0.5230000019073486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7605999708175659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5997999906539917},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5648000240325928},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5430999994277954},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.542900025844574},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5329999923706055},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4377000033855438},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.3718999922275543},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3312999904155731},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28369998931884766},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.25949999690055847}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.06161","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.06161","pdf_url":"https://arxiv.org/pdf/2608.06161","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.2608.06161","doi":"https://doi.org/10.48550/arxiv.2608.06161","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.06161","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.06161","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.06161","pdf_url":"https://arxiv.org/pdf/2608.06161","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4414787395","https://openalex.org/W7128614189","https://openalex.org/W4416097261","https://openalex.org/W7123905905","https://openalex.org/W7168657364","https://openalex.org/W4388796305","https://openalex.org/W7123263844","https://openalex.org/W4382468817","https://openalex.org/W4402727120","https://openalex.org/W7128647072"],"abstract_inverted_index":{"Synthetic":[0],"3D":[1],"scene":[2,64,116,145],"generation":[3,138],"is":[4],"increasingly":[5],"used":[6],"as":[7,133],"a":[8,62,72,127,134,143],"data":[9,37,122,137],"source":[10],"for":[11,38],"computer":[12],"vision":[13],"and":[14,44,81,107,114],"embodied":[15],"AI,":[16],"but":[17],"existing":[18],"generators":[19],"often":[20,49],"optimize":[21],"perceptual":[22],"realism":[23],"without":[24],"reliably":[25],"satisfying":[26],"task-critical":[27],"functional":[28],"constraints.":[29],"This":[30],"mismatch":[31],"limits":[32],"the":[33],"usefulness":[34],"of":[35],"synthetic":[36,136],"downstream":[39],"training,":[40],"where":[41],"accessibility,":[42],"traversability,":[43],"spatial":[45],"rule":[46],"compliance":[47],"are":[48,93],"essential.":[50],"We":[51,118],"present":[52],"iARCS,":[53],"an":[54],"iterative":[55],"agentic":[56],"reinforcement":[57],"learning":[58],"framework":[59],"that":[60,92,121],"adapts":[61],"pretrained":[63],"generator":[65],"to":[66,77],"naturallanguage":[67],"task":[68],"requirements.":[69],"iARCS":[70,125],"uses":[71],"two-phase":[73],"strategy:":[74],"universal-reward":[75],"pretraining":[76],"improve":[78],"physical":[79],"plausibility":[80],"layout":[82],"quality,":[83],"followed":[84],"by":[85,124],"task-specific":[86,111],"finetuning":[87],"with":[88],"LLM-generated":[89],"reward":[90],"programs":[91],"iteratively":[94],"refined":[95],"from":[96],"training":[97],"feedback.":[98],"Experiments":[99],"show":[100,120],"improved":[101],"constraint":[102,112],"fidelity":[103],"on":[104],"walkability,":[105],"reachability,":[106],"clearance-focused":[108],"tasks,":[109],"effective":[110],"optimization,":[113],"competitive":[115],"diversity.":[117],"further":[119],"generated":[123],"improves":[126],"base":[128],"generator,":[129],"supporting":[130],"its":[131],"value":[132],"practical":[135],"tool":[139],"rather":[140],"than":[141],"only":[142],"controllable":[144],"editing":[146],"method.":[147]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-09T00:00:00"}