{"id":"https://openalex.org/W7137927651","doi":"https://doi.org/10.1609/aaai.v40i9.37709","title":"Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning","display_name":"Connecting the Dots: Training-Free Visual Grounding via Agentic Reasoning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137927651","doi":"https://doi.org/10.1609/aaai.v40i9.37709"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i9.37709","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37709","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i9.37709","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129737978","display_name":"Liqin Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liqin Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129691005","display_name":"Guangyao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guangyao Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054226277","display_name":"Xiawu Zheng","orcid":"https://orcid.org/0000-0002-6855-5403"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiawu Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002032727","display_name":"Yongxing Dai","orcid":"https://orcid.org/0000-0003-0176-1138"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongxing Dai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129681083","display_name":"Yixiong Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixiong Zou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129648272","display_name":"Yonghong Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yonghong Tian","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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"9","first_page":"7671","last_page":"7679"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9894000291824341,"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":0.9894000291824341,"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/T10028","display_name":"Topic Modeling","score":0.0012000000569969416,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0010000000474974513,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.6819000244140625},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.607200026512146},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5898000001907349},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5565999746322632},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5315999984741211},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44850000739097595},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4374000132083893},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.41019999980926514},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4059000015258789},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4056999981403351}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731999754905701},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6819000244140625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.626800000667572},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.607200026512146},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5898000001907349},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5565999746322632},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5315999984741211},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4803999960422516},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44850000739097595},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4374000132083893},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4059000015258789},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4056999981403351},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.38350000977516174},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31369999051094055},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.3043000102043152},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2939000129699707},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i9.37709","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37709","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37709","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i9.37709","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37709","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6032043099403381,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4587952244","display_name":null,"funder_award_id":"62027804","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5151253548","display_name":null,"funder_award_id":"62332002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6662223526","display_name":null,"funder_award_id":"61825101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7149955680","display_name":null,"funder_award_id":"20240729102051063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7449767353","display_name":null,"funder_award_id":"2024M750100","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G7858991930","display_name":null,"funder_award_id":"KQTD 20240729102051063","funder_id":"https://openalex.org/F4320326705","funder_display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality"}],"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"},{"id":"https://openalex.org/F4320326705","display_name":"Science, Technology and Innovation Commission of Shenzhen Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0],"grounding,":[1],"the":[2,119,123,126,139],"task":[3],"of":[4,102,142],"linking":[5],"textual":[6],"queries":[7],"to":[8,33,36,83],"specific":[9],"regions":[10,87],"within":[11],"images,":[12],"plays":[13],"a":[14,48,62],"pivotal":[15],"role":[16,141],"in":[17],"vision-language":[18],"integration.":[19],"Existing":[20],"methods":[21],"typically":[22],"rely":[23],"on":[24,104],"extensive":[25],"task-specific":[26,58],"annotations":[27],"and":[28,78,91,137],"fine-tuning,":[29],"limiting":[30],"their":[31],"ability":[32],"generalize":[34],"effectively":[35],"novel":[37,49],"or":[38],"out-of-distribution":[39],"scenarios.":[40],"To":[41],"address":[42],"these":[43],"limitations,":[44],"we":[45],"introduce":[46],"GroundingAgent,":[47],"agentic":[50],"visual":[51],"grounding":[52,100],"framework":[53],"that":[54,67],"operates":[55],"without":[56,111],"any":[57],"fine-tuning.":[59,112],"GroundingAgent":[60,95,146],"employs":[61],"structured,":[63],"iterative":[64],"reasoning":[65,144,154],"mechanism":[66],"integrates":[68],"pretrained":[69],"open-vocabulary":[70],"object":[71],"detectors,":[72],"multimodal":[73],"large":[74,79],"language":[75,80],"models":[76,81],"(MLLMs),":[77],"(LLMs)":[82],"progressively":[84],"refine":[85],"candidate":[86],"through":[88],"joint":[89],"semantic":[90],"spatial":[92],"analyses.":[93],"Remarkably,":[94],"achieves":[96],"an":[97],"average":[98],"zero-shot":[99],"accuracy":[101,124],"65.1%":[103],"widely-used":[105],"benchmarks":[106],"(RefCOCO,":[107],"RefCOCO+,":[108],"RefCOCOg),":[109],"entirely":[110],"Furthermore,":[113],"by":[114],"substituting":[115],"MLLM-generated":[116],"captions":[117],"with":[118],"original":[120],"query":[121],"texts,":[122],"at":[125],"selection":[127],"stage":[128],"alone":[129],"reaches":[130],"approximately":[131],"90%,":[132],"closely":[133],"matching":[134],"supervised":[135],"performance":[136],"underscoring":[138],"critical":[140],"LLM":[143],"capabilities.":[145],"also":[147],"offers":[148],"strong":[149],"interpretability,":[150],"transparently":[151],"illustrating":[152],"each":[153],"step,":[155],"thus":[156],"providing":[157],"clear":[158],"insights":[159],"into":[160],"its":[161],"decision-making":[162],"process.":[163]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}