{"id":"https://openalex.org/W7214917342","doi":"https://doi.org/10.48550/arxiv.2609.37226","title":"Follow the Entities: A Corpus Map for Agentic Search","display_name":"Follow the Entities: A Corpus Map for Agentic Search","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214917342","doi":"https://doi.org/10.48550/arxiv.2609.37226"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.37226","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37226","pdf_url":"https://arxiv.org/pdf/2609.37226","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.37226","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099057789","display_name":"Soyeong Jeong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeong, Soyeong","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036031706","display_name":"Sujay Kumar Jauhar","orcid":"https://orcid.org/0009-0001-9239-6211","observed_orcids":["https://orcid.org/0009-0001-9239-6211"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jauhar, Sujay Kumar","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153575615","display_name":"Sung Ju Hwang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwang, Sung Ju","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019075836","display_name":"Andrew Nam","orcid":"https://orcid.org/0000-0001-9860-4221","observed_orcids":["https://orcid.org/0000-0001-9860-4221"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nam, Andrew Joohun","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5497999787330627,"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/T10028","display_name":"Topic Modeling","score":0.5497999787330627,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.4399000108242035,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.00279999990016222,"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/agentic-search","display_name":"agentic search","score":0.9089999794960022},{"id":"https://openalex.org/keywords/entity-linking","display_name":"entity linking","score":0.6399999856948853},{"id":"https://openalex.org/keywords/large-text-collections","display_name":"large document collections","score":0.7009999752044678},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.8389999866485596},{"id":"https://openalex.org/keywords/discovery-of-evidence","display_name":"discovery of evidence","score":0.824999988079071},{"id":"https://openalex.org/keywords/token-efficiency","display_name":"token efficiency","score":0.765999972820282}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7613999843597412},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6003000140190125},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5899999737739563},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5325000286102295},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5033000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.498199999332428},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.275299996137619},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.37226","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37226","pdf_url":"https://arxiv.org/pdf/2609.37226","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.2609.37226","doi":"https://doi.org/10.48550/arxiv.2609.37226","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.37226","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:2609.37226","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37226","pdf_url":"https://arxiv.org/pdf/2609.37226","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214917342.pdf","grobid_xml":"https://content.openalex.org/works/W7214917342.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2296283641","https://openalex.org/W2962691502","https://openalex.org/W3014295153","https://openalex.org/W3015883388","https://openalex.org/W3032553678","https://openalex.org/W3104748221","https://openalex.org/W3173436410","https://openalex.org/W4321448364","https://openalex.org/W4385270229","https://openalex.org/W4385571271","https://openalex.org/W4389519118","https://openalex.org/W4393065402","https://openalex.org/W4395686609","https://openalex.org/W4401042753","https://openalex.org/W4401043472","https://openalex.org/W4401857375","https://openalex.org/W4416036988","https://openalex.org/W4416037524","https://openalex.org/W6891851425","https://openalex.org/W6892236312","https://openalex.org/W6910735936","https://openalex.org/W7082977246","https://openalex.org/W7133198032","https://openalex.org/W7138462460","https://openalex.org/W7160633197","https://openalex.org/W7160659693","https://openalex.org/W7162429128","https://openalex.org/W7162798635","https://openalex.org/W7165385035","https://openalex.org/W7171849062"],"related_works":["https://openalex.org/W7204226138","https://openalex.org/W7203707532","https://openalex.org/W7162798635","https://openalex.org/W7221086776","https://openalex.org/W7164880517","https://openalex.org/W7172385259","https://openalex.org/W7171505919","https://openalex.org/W7214754187","https://openalex.org/W7204107397","https://openalex.org/W7135232565"],"abstract_inverted_index":{"Answering":[0],"questions":[1],"and":[2,29,126,152,166,222,235],"completing":[3],"tasks":[4],"over":[5,225],"large":[6,251],"document":[7,72,131,156,252],"collections":[8],"often":[9,92],"requires":[10],"connecting":[11],"evidence":[12,95,220],"spread":[13],"across":[14,135,191,197],"multiple":[15],"documents,":[16,192],"such":[17],"as":[18,64,143,246],"a":[19,34,51,65,70,108,129,162],"project's":[20],"approval":[21],"recorded":[22],"in":[23,27,33],"one,":[24],"its":[25,30,116,193],"requirements":[26],"another,":[28],"latest":[31],"status":[32],"third.":[35],"Recent":[36],"LLM":[37],"agents":[38],"approach":[39],"this":[40],"by":[41,184],"iteratively":[42],"searching":[43],"the":[44,59,83,113,123,169,188],"full":[45],"corpus":[46,60,114],"rather":[47,199],"than":[48,200],"reading":[49],"only":[50,63],"fixed":[52],"set":[53],"of":[54,68,76,187],"top-ranked":[55],"documents.":[56],"However,":[57],"when":[58],"is":[61,181],"exposed":[62],"flat":[66],"collection":[67],"files,":[69],"relevant":[71],"gives":[73],"no":[74],"indication":[75],"how":[77],"it":[78,151],"relates":[79],"to":[80,132,154,159,173],"others,":[81],"so":[82],"agent":[84,170],"must":[85],"rediscover":[86],"these":[87],"relationships":[88],"for":[89,249],"every":[90,155],"query,":[91],"missing":[93],"complementary":[94],"while":[96,229],"simultaneously":[97],"consuming":[98],"substantial":[99],"additional":[100],"tokens.":[101],"To":[102],"address":[103],"this,":[104],"we":[105,214],"introduce":[106],"CorpusMap,":[107],"navigation":[109,240],"layer":[110],"that":[111,147,157,168,216,243],"organizes":[112],"around":[115],"recurring":[117,141],"entities,":[118],"which":[119],"are":[120,195],"identifiable":[121],"from":[122],"documents":[124,167],"themselves":[125],"can":[127,171],"link":[128],"single":[130],"many":[133],"others":[134],"sources.":[136],"Specifically,":[137],"CorpusMap":[138,180,217],"represents":[139],"each":[140],"entity":[142,190],"an":[144],"Entity":[145],"Page":[146],"aggregates":[148],"information":[149],"about":[150],"links":[153,194],"refers":[158],"it,":[160],"forming":[161],"graph":[163],"between":[164],"entities":[165,244],"traverse":[172],"gather":[174],"otherwise":[175],"disconnected":[176],"evidence.":[177],"Moreover,":[178],"since":[179],"constructed":[182],"offline":[183],"resolving":[185],"mentions":[186],"same":[189],"shared":[196],"queries":[198],"rediscovered":[201],"repeatedly":[202],"at":[203],"inference":[204],"time.":[205],"Using":[206],"7":[207],"different":[208],"models":[209],"with":[210],"3":[211],"benchmark":[212],"datasets,":[213],"show":[215],"improves":[218],"both":[219],"discovery":[221],"answer":[223],"quality":[224],"raw-corpus":[226],"agentic":[227],"search":[228],"using":[230],"fewer":[231],"tokens":[232],"on":[233],"average,":[234],"further":[236],"outperforms":[237],"4":[238],"alternative":[239],"layers,":[241],"suggesting":[242],"serve":[245],"effective":[247],"anchors":[248],"navigating":[250],"collections.":[253]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}