{"id":"https://openalex.org/W7155220216","doi":"https://doi.org/10.1109/tvcg.2026.3686395","title":"SIAgent: Spatial Interaction Agent via LLM-Powered Eye-Hand Motion Intent Understanding in VR","display_name":"SIAgent: Spatial Interaction Agent via LLM-Powered Eye-Hand Motion Intent Understanding in VR","publication_year":2026,"publication_date":"2026-04-22","ids":{"openalex":"https://openalex.org/W7155220216","doi":"https://doi.org/10.1109/tvcg.2026.3686395","pmid":"https://pubmed.ncbi.nlm.nih.gov/42019061"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2026.3686395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2026.3686395","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013724447","display_name":"Z X Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhimin Wang","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5089-977X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134230679","display_name":"Chenyu Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyu Gu","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134233283","display_name":"Feng Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Lu","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9064-7964","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38647789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"7","first_page":"6683","last_page":"6694"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.6115999817848206,"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"}},"topics":[{"id":"https://openalex.org/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.6115999817848206,"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"}},{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.0697999969124794,"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"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.051500000059604645,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5199000239372253},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.49799999594688416},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.48980000615119934},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.3684000074863434},{"id":"https://openalex.org/keywords/3d-interaction","display_name":"3D interaction","score":0.31859999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918999791145325},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5199000239372253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5066999793052673},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.49799999594688416},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49230000376701355},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4657000005245209},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.3684000074863434},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.35749998688697815},{"id":"https://openalex.org/C2776977519","wikidata":"https://www.wikidata.org/wiki/Q4636326","display_name":"3D interaction","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C2777036941","wikidata":"https://www.wikidata.org/wiki/Q6917771","display_name":"Motion analysis","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.2732999920845032}],"mesh":[{"descriptor_ui":"D000076142","descriptor_name":"Virtual Reality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003196","descriptor_name":"Computer Graphics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005133","descriptor_name":"Eye Movements","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005868","descriptor_name":"Gestures","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006225","descriptor_name":"Hand","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008297","descriptor_name":"Male","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D033182","descriptor_name":"Intention","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tvcg.2026.3686395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2026.3686395","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:42019061","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42019061","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on visualization and computer graphics","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1876018573","display_name":null,"funder_award_id":"62502020","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2177286772","display_name":null,"funder_award_id":"2025M774238","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G6976983210","display_name":null,"funder_award_id":"62372019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1991087539","https://openalex.org/W2042751882","https://openalex.org/W2137864660","https://openalex.org/W2151905266","https://openalex.org/W2796228338","https://openalex.org/W2888827598","https://openalex.org/W2905309298","https://openalex.org/W3091007149","https://openalex.org/W3094625080","https://openalex.org/W3163078982","https://openalex.org/W3199591511","https://openalex.org/W3206939027","https://openalex.org/W4224252713","https://openalex.org/W4225093743","https://openalex.org/W4294068677","https://openalex.org/W4294068695","https://openalex.org/W4318977964","https://openalex.org/W4361771142","https://openalex.org/W4367662589","https://openalex.org/W4367662816","https://openalex.org/W4387250059","https://openalex.org/W4389296606","https://openalex.org/W4390729541","https://openalex.org/W4392405485","https://openalex.org/W4392450191","https://openalex.org/W4394805681","https://openalex.org/W4394811216","https://openalex.org/W4394825462","https://openalex.org/W4394825470","https://openalex.org/W4396832611","https://openalex.org/W4402389462","https://openalex.org/W4403842152","https://openalex.org/W4404848616","https://openalex.org/W4404966227","https://openalex.org/W4408147583","https://openalex.org/W4408324565","https://openalex.org/W4408954469","https://openalex.org/W4411814566","https://openalex.org/W4414983863","https://openalex.org/W7084032685","https://openalex.org/W7123360223","https://openalex.org/W7160182044"],"related_works":[],"abstract_inverted_index":{"Eye-hand":[0],"coordinated":[1],"interaction":[2,7,20,49,66,90,135,157,194],"is":[3],"becoming":[4],"a":[5,58],"mainstream":[6],"modality":[8],"in":[9,183],"Virtual":[10],"Reality":[11],"(VR)":[12],"user":[13,97,130,169],"interfaces.":[14],"Current":[15],"paradigms":[16],"for":[17,115],"this":[18,53],"multimodal":[19],"require":[21],"users":[22,63],"to":[23,64,107],"learn":[24],"predefined":[25],"gestures":[26],"and":[27,46,76,95,99,118,165,168,179],"memorize":[28],"multiple":[29],"gesture-task":[30],"associations,":[31],"which":[32],"can":[33],"be":[34],"summarized":[35],"as":[36],"an":[37,105],"\"Operation-to-Intent\"":[38,142],"paradigm.":[39],"This":[40,111],"paradigm":[41],"increases":[42],"users'":[43],"learning":[44],"costs":[45],"has":[47],"low":[48],"error":[50,125],"tolerance.":[51,126],"In":[52],"paper,":[54],"we":[55],"propose":[56],"SIAgent,":[57],"novel":[59],"\"Intent-to-Operation\"":[60],"framework":[61],"allowing":[62],"express":[65],"intents":[67],"through":[68,196],"natural":[69,93],"eye-hand":[70],"motions":[71],"based":[72],"on":[73],"common":[74],"sense":[75],"habits.":[77],"Our":[78,186],"system":[79],"features":[80],"two":[81,129,141],"main":[82],"components:":[83],"(1)":[84],"intent":[85,150,184],"recognition":[86,151],"that":[87,103],"translates":[88],"spatial":[89],"data":[91],"into":[92,191],"language":[94],"infers":[96],"intent,":[98],"(2)":[100],"agent-based":[101],"execution":[102],"generates":[104],"agent":[106],"execute":[108],"corresponding":[109],"tasks.":[110],"eliminates":[112],"the":[113,174],"need":[114],"gesture":[116],"memorization":[117],"accommodates":[119],"individual":[120],"motion":[121,181],"preferences":[122],"with":[123,140],"high":[124],"We":[127],"conduct":[128],"studies":[131],"across":[132],"over":[133],"60":[134],"tasks,":[136],"comparing":[137],"our":[138,146],"method":[139,147],"techniques.":[143],"Results":[144],"show":[145],"achieves":[148],"higher":[149],"accuracy":[152],"than":[153],"gaze":[154,178],"+":[155],"pinch":[156],"(97.2%":[158],"versus":[159],"93.1%)":[160],"while":[161],"reducing":[162],"arm":[163],"fatigue":[164],"improving":[166],"usability,":[167],"preference.":[170],"Another":[171],"study":[172],"verifies":[173],"function":[175],"of":[176],"eye":[177],"hand":[180],"channels":[182],"recognition.":[185],"work":[187],"offers":[188],"valuable":[189],"insights":[190],"enhancing":[192],"VR":[193],"intelligence":[195],"intent-driven":[197],"design.":[198]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-04-23T00:00:00"}
