{"id":"https://openalex.org/W7204887919","doi":"https://doi.org/10.18653/2026.emnlp-main.1984","title":"Perceive to Hypothesize, Verify to Ground: an Agentic Reasoning Framework for Open-World Geo-Localization","display_name":"Perceive to Hypothesize, Verify to Ground: an Agentic Reasoning Framework for Open-World Geo-Localization","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204887919","doi":"https://doi.org/10.18653/2026.emnlp-main.1984"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.1984","doi":"https://doi.org/10.18653/2026.emnlp-main.1984","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1984","pdf_url":"https://aclanthology.org/2026.emnlp-main.1984.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-main.1984.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059494004","display_name":"Yutian Jiang","orcid":"https://orcid.org/0009-0008-3800-1144","observed_orcids":["https://orcid.org/0009-0008-3800-1144"]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutian Jiang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148869793","display_name":"Ruijie Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruijie Li","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119959702","display_name":"Sisuo Lyu","orcid":"https://orcid.org/0009-0001-0493-6880","observed_orcids":["https://orcid.org/0009-0001-0493-6880"]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Sisuo Lyu","raw_affiliation_strings":["The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144334413","display_name":"Xixuan Hao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xixuan Hao","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148848682","display_name":"Qingxiang Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingxiang Liu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109714988","display_name":"Yongzi Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongzi Yu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148920742","display_name":"Yuxuan Liang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Liang","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou )"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou )","institution_ids":["https://openalex.org/I4405261251"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.70598838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"45132","last_page":"45153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7006999850273132,"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":0.7006999850273132,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.15320000052452087,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.020500000566244125,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/agentic-reasoning","display_name":"agentic reasoning","score":0.9079999923706055},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.6039999723434448},{"id":"https://openalex.org/keywords/context-drift","display_name":"context drift","score":0.7950000166893005},{"id":"https://openalex.org/keywords/hypothesis-generation","display_name":"hypothesis generation","score":0.7149999737739563},{"id":"https://openalex.org/keywords/evidence-grounding","display_name":"evidence grounding","score":0.906000018119812},{"id":"https://openalex.org/keywords/multi-step-reasoning","display_name":"multi-step reasoning","score":0.6140000224113464},{"id":"https://openalex.org/keywords/tool-invocation","display_name":"tool invocation","score":0.5879999995231628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.695900022983551},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6254000067710876},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5810999870300293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5149000287055969},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.45910000801086426},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.4422999918460846},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.44020000100135803},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3734000027179718},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.367000013589859},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34779998660087585},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34299999475479126},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3416999876499176},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.33309999108314514},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.30959999561309814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30250000953674316},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C183521366","wikidata":"https://www.wikidata.org/wiki/Q7256422","display_name":"Psychology of reasoning","level":4,"score":0.2782000005245209},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.2565000057220459},{"id":"https://openalex.org/C2776325391","wikidata":"https://www.wikidata.org/wiki/Q6917865","display_name":"Motivated reasoning","level":3,"score":0.2563999891281128},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.1984","doi":"https://doi.org/10.18653/2026.emnlp-main.1984","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1984","pdf_url":"https://aclanthology.org/2026.emnlp-main.1984.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.29880","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.29880","pdf_url":"https://arxiv.org/pdf/2608.29880","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.29880","doi":"https://doi.org/10.48550/arxiv.2608.29880","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.29880","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.emnlp-main.1984","doi":"https://doi.org/10.18653/2026.emnlp-main.1984","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1984","pdf_url":"https://aclanthology.org/2026.emnlp-main.1984.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2980890007","display_name":null,"funder_award_id":"2024A03J0628","funder_id":"https://openalex.org/F4320335480","funder_display_name":"Guangzhou Municipal Science and Technology Project"},{"id":"https://openalex.org/G4398489841","display_name":null,"funder_award_id":"2024A03J0628","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G537185493","display_name":null,"funder_award_id":"2023A03J0011","funder_id":"https://openalex.org/F4320335480","funder_display_name":"Guangzhou Municipal Science and Technology Project"},{"id":"https://openalex.org/G6491101664","display_name":null,"funder_award_id":"2025A1515011994","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G7162037129","display_name":null,"funder_award_id":"2023B1212010007","funder_id":"https://openalex.org/F4320335480","funder_display_name":"Guangzhou Municipal Science and Technology Project"},{"id":"https://openalex.org/G8238644607","display_name":null,"funder_award_id":"2023B1212010007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8344050396","display_name":null,"funder_award_id":"62402414","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/F4320335480","display_name":"Guangzhou Municipal Science and Technology Project","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204887919.pdf","grobid_xml":"https://content.openalex.org/works/W7204887919.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7128607081","https://openalex.org/W7106302176","https://openalex.org/W4415312609","https://openalex.org/W4400141283","https://openalex.org/W7163045470","https://openalex.org/W7169689228","https://openalex.org/W4414689495","https://openalex.org/W7138516009","https://openalex.org/W7162563356","https://openalex.org/W4414758349"],"abstract_inverted_index":{"Open-world":[0],"geo-localization":[1,48],"requires":[2],"models":[3,20],"to":[4,37],"reason":[5],"over":[6],"ambiguous":[7],"visual":[8],"cues":[9],"through":[10],"multi-step":[11],"reasoning":[12,24,53,102],"and":[13,33,55,72,81,110,115],"external":[14],"knowledge":[15],"grounding.While":[16],"recent":[17],"large":[18],"vision-language":[19],"exhibit":[21],"strong":[22],"multimodal":[23],"capabilities,":[25],"existing":[26],"approaches":[27],"still":[28],"suffer":[29],"from":[30,94],"perceptual":[31],"hallucination":[32],"context":[34],"drift":[35],"due":[36],"the":[38],"lack":[39],"of":[40],"explicit":[41],"evidence-grounded":[42],"verification.In":[43],"this":[44],"work,":[45],"we":[46,86],"reformulate":[47],"as":[49],"a":[50,60,90],"human-like":[51],"perceivethen-verify":[52],"problem":[54],"propose":[56],"GeoPAVE":[57],"(Geo-localization":[58],"Perception-and-Verification-Engine),":[59],"bi-level":[61],"agentic":[62],"framework":[63],"that":[64],"contains":[65],"perception-based":[66],"hypothesis":[67],"generation":[68],"via":[69],"single-pass":[70],"rollouts":[71],"verification-based":[73],"evidence":[74],"grounding":[75],"for":[76],"decision":[77],"actions:":[78],"support,":[79],"refute,":[80],"refine.To":[82],"support":[83],"rigorous":[84],"evaluation,":[85],"further":[87],"introduce":[88],"PAVED,":[89],"novel":[91],"dataset":[92,114],"derived":[93],"real-world":[95],"user":[96],"check-in":[97],"data,":[98],"equipped":[99],"with":[100],"comprehensive":[101],"trajectories":[103],"featuring":[104],"multi-hop":[105],"queries,":[106],"multi-round":[107],"tool":[108],"invocations,":[109],"structured":[111],"perception-verification":[112],"traces.The":[113],"code":[116],"are":[117],"available":[118],"at":[119],"https://github.com/Arandinglv/GeoPAVE.":[120]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-09-02T00:00:00"}