{"id":"https://openalex.org/W7196922845","doi":"https://doi.org/10.1145/3770855.3818386","title":"DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News Retrieval","display_name":"DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News Retrieval","publication_year":2026,"publication_date":"2026-08-06","ids":{"openalex":"https://openalex.org/W7196922845","doi":"https://doi.org/10.1145/3770855.3818386"},"language":"en","primary_location":{"id":"doi:10.1145/3770855.3818386","doi":"https://doi.org/10.1145/3770855.3818386","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770855.3818386","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3770855.3818386","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137684568","display_name":"Siyuan Qi","orcid":"https://orcid.org/0009-0009-3445-918X","observed_orcids":["https://orcid.org/0009-0009-3445-918X"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Qi","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-3445-918X","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137564474","display_name":"Xinyuan Wang","orcid":"https://orcid.org/0009-0008-4255-9749","observed_orcids":["https://orcid.org/0009-0008-4255-9749"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyuan Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-4255-9749","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087524444","display_name":"Yingxuan Yang","orcid":"https://orcid.org/0000-0002-0494-7440","observed_orcids":["https://orcid.org/0000-0002-0494-7440"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingxuan Yang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0494-7440","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137614263","display_name":"Haochuan Guo","orcid":"https://orcid.org/0009-0008-1390-1162","observed_orcids":["https://orcid.org/0009-0008-1390-1162"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haochuan Guo","raw_affiliation_strings":["Orion Arm AI, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0008-1390-1162","affiliations":[{"raw_affiliation_string":"Orion Arm AI, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036057873","display_name":"Jianghao Lin","orcid":"https://orcid.org/0000-0002-8953-3203","observed_orcids":["https://orcid.org/0000-0002-8953-3203"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianghao Lin","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8953-3203","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101500385","display_name":"Weiwen Liu","orcid":"https://orcid.org/0000-0002-9148-3997","observed_orcids":["https://orcid.org/0000-0002-9148-3997"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwen Liu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9148-3997","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064534815","display_name":"Yong Yu","orcid":"https://orcid.org/0000-0003-4457-2820","observed_orcids":["https://orcid.org/0000-0003-4457-2820"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Yu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4457-2820","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090720315","display_name":"Weinan Zhang","orcid":"https://orcid.org/0000-0002-0127-2425","observed_orcids":["https://orcid.org/0000-0002-0127-2425"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weinan Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0127-2425","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7854","last_page":"7865"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.002899999963119626,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/agentic-retrieval-augmented-generation","display_name":"agentic retrieval-augmented generation","score":0.9200000166893005},{"id":"https://openalex.org/keywords/news-retrieval","display_name":"news retrieval","score":0.8790000081062317},{"id":"https://openalex.org/keywords/semantic-extension","display_name":"semantic extension","score":0.5479999780654907},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6150000095367432},{"id":"https://openalex.org/keywords/a-b-testing","display_name":"A/B testing","score":0.5979999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7698000073432922},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6660000085830688},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5824000239372253},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5490000247955322},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.534500002861023},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5263000130653381},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.48649999499320984},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4352000057697296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4284000098705292},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36800000071525574},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32910001277923584},{"id":"https://openalex.org/C21025794","wikidata":"https://www.wikidata.org/wiki/Q5141219","display_name":"Cognitive models of information retrieval","level":4,"score":0.31779998540878296},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.31769999861717224},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28049999475479126},{"id":"https://openalex.org/C2779532271","wikidata":"https://www.wikidata.org/wiki/Q445558","display_name":"Relevance feedback","level":4,"score":0.2671000063419342},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3770855.3818386","doi":"https://doi.org/10.1145/3770855.3818386","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770855.3818386","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3770855.3818386","doi":"https://doi.org/10.1145/3770855.3818386","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770855.3818386","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1993692165","https://openalex.org/W1993972354","https://openalex.org/W2108280221","https://openalex.org/W2155467656","https://openalex.org/W2167355161","https://openalex.org/W2473408052","https://openalex.org/W2741307002","https://openalex.org/W3039017601","https://openalex.org/W3153833878","https://openalex.org/W4246858749","https://openalex.org/W4304195432","https://openalex.org/W4385565351","https://openalex.org/W4389518671","https://openalex.org/W4389984066","https://openalex.org/W4393065402","https://openalex.org/W4395686609","https://openalex.org/W4402684046","https://openalex.org/W4406542750","https://openalex.org/W4407123696","https://openalex.org/W4411119292","https://openalex.org/W4412889884","https://openalex.org/W4414014501","https://openalex.org/W4416035089","https://openalex.org/W4416068048","https://openalex.org/W4417152688","https://openalex.org/W6948369276","https://openalex.org/W7133222210"],"related_works":["https://openalex.org/W7139961658","https://openalex.org/W7221086776","https://openalex.org/W7118400800","https://openalex.org/W7130609696","https://openalex.org/W4415191102","https://openalex.org/W4415276736","https://openalex.org/W7165177996","https://openalex.org/W4416285354","https://openalex.org/W6903875708","https://openalex.org/W4403577942"],"abstract_inverted_index":{"Agentic":[0,51],"Retrieval-Augmented":[1],"Generation":[2],"(RAG)":[3],"improves":[4,227],"retrieval":[5,25,69,89,103,114,135],"by":[6],"integrating":[7],"planning,":[8],"tool":[9],"use,":[10],"and":[11,36,108,172,182,188,203,247,279],"iterative":[12],"reasoning,":[13,160],"but":[14],"most":[15],"existing":[16,250],"agentic":[17,59,73,82,159,190,270],"RAG":[18,60,83,187],"methods":[19],"tightly":[20],"couple":[21],"semantic":[22,65,99,123],"expansion":[23],"with":[24,147,223],"decisions":[26],"within":[27],"short-horizon":[28],"inference":[29,34],"loops,":[30],"resulting":[31],"in":[32,57,198,276],"high":[33],"costs":[35],"limited":[37],"suitability":[38],"for":[39,63,91,153,281],"time-sensitive,":[40],"high-recall":[41],"tasks":[42],"such":[43],"as":[44,132],"news":[45,170,283],"retrieval.":[46,284],"We":[47],"propose":[48],"DynaTree":[49,79,129,178,193,267],"(Dynamic":[50],"Retrieval":[52],"Tree),":[53],"a":[54,87,117,133,143,243],"two-stage":[55],"framework":[56],"which":[58],"is":[61,70],"used":[62,151],"offline":[64,271],"exploration,":[66],"while":[67],"online":[68,206,258],"performed":[71],"without":[72,157],"inference.":[74],"In":[75,125],"the":[76,111,121,126,199,219],"first":[77],"stage,":[78,128],"adopts":[80],"an":[81],"process":[84],"to":[85,212,232,239],"construct":[86],"reusable":[88],"tree":[90,112,161],"each":[92],"query":[93],"topic,":[94],"where":[95],"coordinated":[96],"agents":[97],"plan":[98],"expansions,":[100],"execute":[101],"diverse":[102],"strategies,":[104],"normalize":[105],"retrieved":[106],"evidence,":[107],"iteratively":[109],"refine":[110],"using":[113],"feedback,":[115],"materializing":[116],"persistent":[118],"representation":[119],"of":[120,237],"query's":[122],"space.":[124],"second":[127],"operates":[130],"purely":[131],"structure-aware":[134],"system,":[136],"performing":[137],"lightweight":[138],"daily":[139,224],"subtree":[140,225,246],"selection":[141,226],"over":[142,242],"time-localized":[144],"evaluation":[145,255],"proxy,":[146],"large":[148],"language":[149],"models":[150],"only":[152],"rapid":[154],"relevance":[155,280],"labeling,":[156],"further":[158],"modification,":[162],"or":[163],"retraining.":[164],"Experiments":[165],"on":[166,253],"our":[167],"multi-day":[168],"Syft":[169,200],"benchmark":[171],"multiple":[173],"BEIR":[174],"datasets":[175],"show":[176],"that":[177,266],"achieves":[179],"state-of-the-art":[180],"recall":[181],"NDCG,":[183],"consistently":[184],"outperforming":[185,248],"standard":[186],"prior":[189],"baselines.":[191],"Moreover,":[192],"has":[194],"been":[195],"directly":[196],"deployed":[197],"production":[201,251],"system":[202],"evaluated":[204],"through":[205],"A/B":[207],"testing":[208],"from":[209,230],"Jan.":[210],"28":[211],"Feb.":[213],"6,":[214],"2026.":[215],"Across":[216],"all":[217,249],"days,":[218],"dynamically":[220],"adapted":[221],"variant":[222],"survival":[228],"rate":[229],"0.32-0.53":[231],"0.59-0.73,":[233],"yielding":[234],"consistent":[235],"gains":[236,259],"up":[238],"\u223c":[240],"1.5\u00d7":[241],"fixed":[244],"offline-selected":[245],"recallers":[252],"every":[254],"day.":[256],"These":[257],"persist":[260],"under":[261],"live":[262],"user":[263],"traffic,":[264],"demonstrating":[265],"translates":[268],"structure-aware,":[269],"reasoning":[272],"into":[273],"tangible":[274],"improvements":[275],"coverage,":[277],"freshness,":[278],"real-world":[282]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-08-07T00:00:00"}