{"id":"https://openalex.org/W7204888959","doi":"https://doi.org/10.48550/arxiv.2608.31082","title":"Agentic Context Cracking: Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured Data","display_name":"Agentic Context Cracking: Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured Data","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7204888959","doi":"https://doi.org/10.48550/arxiv.2608.31082"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.31082","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.31082","pdf_url":"https://arxiv.org/pdf/2608.31082","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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.31082","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006345217","display_name":"Milad Rezaei Hajidehi","orcid":"https://orcid.org/0000-0003-2410-1052","observed_orcids":["https://orcid.org/0000-0003-2410-1052"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hajidehi, Milad Rezaei","raw_affiliation_strings":["Harvard University Cambridge , Massachusetts , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University Cambridge , Massachusetts , USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101488348","display_name":"Qitong Wang","orcid":"https://orcid.org/0000-0001-6360-3800","observed_orcids":["https://orcid.org/0000-0001-6360-3800"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Qitong","raw_affiliation_strings":["Harvard University Cambridge , Massachusetts , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University Cambridge , Massachusetts , USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026905380","display_name":"Stratos Idreos","orcid":"https://orcid.org/0000-0002-8271-9187","observed_orcids":["https://orcid.org/0000-0002-8271-9187"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Idreos, Stratos","raw_affiliation_strings":["Harvard University Cambridge , Massachusetts , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University Cambridge , Massachusetts , USA","institution_ids":["https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I136199984"],"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":0.8960000276565552,"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":0.8960000276565552,"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":0.03779999911785126,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.01979999989271164,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/unstructured-data-structuring","display_name":"unstructured data structuring","score":0.8130000233650208},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.7480000257492065},{"id":"https://openalex.org/keywords/token-efficiency","display_name":"token efficiency","score":0.6710000038146973},{"id":"https://openalex.org/keywords/knowledge-workers","display_name":"knowledge workers","score":0.3400000035762787},{"id":"https://openalex.org/keywords/enterprise-ai","display_name":"enterprise AI","score":0.6420000195503235},{"id":"https://openalex.org/keywords/data-infrastructure","display_name":"data infrastructure","score":0.5120000243186951}],"concepts":[{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.7919999957084656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878999710083008},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.7680000066757202},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5594000220298767},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5001000165939331},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.43299999833106995},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4092000126838684},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38850000500679016},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3109000027179718},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2957000136375427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2896000146865845},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C186625053","wikidata":"https://www.wikidata.org/wiki/Q1130191","display_name":"Information overload","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.2791999876499176}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.31082","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.31082","pdf_url":"https://arxiv.org/pdf/2608.31082","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.2608.31082","doi":"https://doi.org/10.48550/arxiv.2608.31082","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.31082","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":"pmh:oai:arXiv.org:2608.31082","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.31082","pdf_url":"https://arxiv.org/pdf/2608.31082","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204888959.pdf","grobid_xml":"https://content.openalex.org/works/W7204888959.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4389520779","https://openalex.org/W7203868003","https://openalex.org/W7212305821","https://openalex.org/W7214067847","https://openalex.org/W7160442321","https://openalex.org/W7135067556","https://openalex.org/W7172266015","https://openalex.org/W4409149511","https://openalex.org/W7140171824","https://openalex.org/W7162084384"],"abstract_inverted_index":{"Valuable":[0],"data":[1,30,67,143,150,223,258,266],"remains":[2],"embedded":[3],"in":[4,19,113],"unstructured":[5,149,272],"sources:":[6],"web":[7],"pages,":[8],"reports,":[9],"contracts,":[10],"filings,":[11],"earnings":[12],"calls,":[13],"and":[14,95,129,133,152,170,173,201,224],"PDFs.":[15],"The":[16],"big":[17],"bet":[18],"enterprise":[20],"AI":[21],"is":[22,92,115,161,218,260],"deploying":[23],"LLM":[24],"agents":[25],"that":[26,147,282],"reason":[27],"over":[28,87,107,271],"this":[29,42],"to":[31,54,60,76,99,188,206,235,286],"answer":[32],"complex":[33],"questions":[34,104],"for":[35,268],"every":[36],"knowledge":[37,281],"worker.":[38],"Agents":[39],"can":[40],"do":[41],"today,":[43],"but":[44],"at":[45,198,233],"prohibitive":[46],"cost.":[47,237],"Each":[48],"question":[49,73,245],"repeatedly":[50],"opens":[51,185],"large":[52],"documents":[53,118,134],"recover":[55],"scattered":[56],"evidence,":[57],"consuming":[58],"up":[59],"a":[61,77,145,155,186,190,228,261,274],"million":[62],"tokens.":[63],"However,":[64],"if":[65],"the":[66,71,96,130,179,183,195,278],"were":[68],"already":[69,284],"structured,":[70],"same":[72],"would":[74],"reduce":[75],"cheap":[78],"database":[79],"lookup.":[80],"For":[81],"example,":[82],"on":[83],"FanOutQA":[84],"benchmark,":[85],"reasoning":[86,158,270,283],"an":[88,213],"ideal":[89],"pre-structured":[90],"store":[91],"28X":[93],"cheaper,":[94],"gap":[97],"grows":[98],"orders":[100],"of":[101,157,216],"magnitude":[102],"as":[103,154],"fan":[105],"out":[106],"more":[108,121],"documents.":[109],"Yet":[110],"structuring":[111],"everything":[112],"advance":[114],"not":[116],"viable:":[117],"hold":[119],"vastly":[120],"possible":[122],"structure":[123,132,204],"than":[124],"any":[125],"workload":[126],"will":[127],"use,":[128],"useful":[131],"are":[135],"unknown":[136],"until":[137],"queries":[138,165,217],"arrive.":[139],"We":[140],"propose":[141],"agentic":[142,231,269],"cracking,":[144],"method":[146],"structures":[148],"adaptively":[151],"speculatively":[153],"byproduct":[156],"itself.":[159],"Structuring":[160],"adaptive":[162],"because":[163,175],"observed":[164],"decide":[166],"when":[167],"it":[168,176],"happens":[169],"what":[171],"matters,":[172],"speculative":[174],"goes":[177],"beyond":[178],"current":[180],"question.":[181],"Whenever":[182],"agent":[184],"document":[187],"answer,":[189],"cracking":[191,249,259],"sub-agent":[192],"forks":[193],"from":[194],"already-loaded":[196],"context":[197],"marginal":[199],"cost":[200,251],"extracts":[202],"grounded":[203],"likely":[205],"serve":[207],"related":[208,244],"future":[209],"queries.":[210],"Over":[211],"time,":[212],"increasing":[214],"share":[215],"fully":[219],"covered":[220],"by":[221,252],"structured":[222],"answered":[225],"without":[226],"opening":[227],"document,":[229],"keeping":[230],"accuracy":[232],"close":[234],"RAG":[236],"On":[238],"FanOutQA,":[239],"extended":[240],"with":[241],"merely":[242],"one":[243],"per":[246],"test":[247],"question,":[248],"cuts":[250],"53%":[253],"while":[254],"preserving":[255],"accuracy.":[256],"Agentic":[257],"first":[262],"step":[263],"toward":[264],"next-generation":[265],"infrastructure":[267],"data:":[273],"shared":[275],"substrate":[276],"beneath":[277],"model":[279],"where":[280],"paid":[285],"uncover":[287],"accumulates.":[288]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-02T00:00:00"}