{"id":"https://openalex.org/W7125822268","doi":"https://doi.org/10.48550/arxiv.2601.18116","title":"BEAR: Budgeted Evidence Allocation for Multi-Document Reasoning","display_name":"BEAR: Budgeted Evidence Allocation for Multi-Document Reasoning","publication_year":2026,"publication_date":"2026-01-26","ids":{"openalex":"https://openalex.org/W7125822268","doi":"https://doi.org/10.48550/arxiv.2601.18116"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2601.18116","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.18116","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2601.18116","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124023162","display_name":"Lin Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123935202","display_name":"Linglin Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Linglin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123926940","display_name":"Jingang Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Jingang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123971832","display_name":"Change Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Change","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124049849","display_name":"Zhengwei Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Zhengwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124030030","display_name":"Xiangzheng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiangzheng","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":false,"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":0.6815000176429749,"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":0.6815000176429749,"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":0.09950000047683716,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.039400000125169754,"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/inference","display_name":"Inference","score":0.7005000114440918},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.5967000126838684},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5945000052452087},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4575999975204468},{"id":"https://openalex.org/keywords/fable","display_name":"Fable","score":0.43470001220703125},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4154999852180481},{"id":"https://openalex.org/keywords/empirical-evidence","display_name":"Empirical evidence","score":0.33390000462532043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7576000094413757},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7005000114440918},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.5967000126838684},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5945000052452087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5397999882698059},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4575999975204468},{"id":"https://openalex.org/C2778662471","wikidata":"https://www.wikidata.org/wiki/Q693","display_name":"Fable","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36629998683929443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36390000581741333},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.32030001282691956},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2601.18116","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.18116","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2601.18116","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.18116","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,62],"argue":[1],"that":[2,55,71,153],"multi-document":[3],"reasoning":[4],"is":[5,25],"constrained":[6],"not":[7],"only":[8],"by":[9,19],"how":[10,20],"much":[11],"text":[12],"a":[13,65,102],"model":[14,36],"can":[15,94],"read,":[16],"but":[17],"also":[18],"limited":[21],"query-time":[22],"evidence":[23,39,69,80,99,143],"budget":[24],"allocated":[26],"across":[27],"documents":[28],"and":[29,41,77,88,108,125,168],"semantic":[30,74,172],"granularities.":[31],"Full-context":[32],"inference":[33],"exposes":[34],"the":[35,127,146,154],"to":[37],"broad":[38],"non-selectively":[40],"at":[42,82],"high":[43],"per-query":[44],"cost,":[45],"while":[46,137],"flat":[47],"chunk":[48],"retrieval":[49],"often":[50],"returns":[51],"locally":[52],"relevant":[53],"passages":[54],"are":[56,156],"weakly":[57],"organized":[58],"for":[59,67],"cross-document":[60],"synthesis.":[61],"present":[63],"\\textbf{BEAR},":[64],"framework":[66],"structured":[68,98],"allocation":[70,100,162],"builds":[72],"hierarchical":[73],"indices":[75],"offline":[76],"performs":[78,112],"coarse-to-fine":[79,92],"access":[81],"query":[83],"time":[84],"through":[85],"complementary":[86,166],"\\emph{exploration}":[87],"\\emph{recovery}":[89],"paths.":[90],"This":[91],"design":[93],"be":[95],"viewed":[96],"as":[97,160],"under":[101,133,139],"fixed":[103],"evidence-context":[104],"budget.":[105],"Across":[106],"synthetic":[107],"real-world":[109],"benchmarks,":[110],"BEAR":[111],"particularly":[113],"strongly":[114],"on":[115,123,131],"DragonBall,":[116],"remains":[117],"competitive":[118],"with":[119,158,165],"strong":[120],"retrieval-based":[121,129],"baselines":[122],"HotpotQA,":[124],"yields":[126],"best":[128],"result":[130],"2Wiki":[132],"our":[134],"evaluated":[135],"protocol,":[136],"operating":[138],"substantially":[140],"smaller":[141],"\\emph{query-time":[142],"budgets}":[144],"than":[145,171],"reported":[147],"long-context":[148],"references.":[149],"Additional":[150],"analyses":[151],"suggest":[152],"gains":[155],"associated":[157],"hierarchy":[159],"an":[161],"substrate":[163],"together":[164],"exploration":[167],"recovery,":[169],"rather":[170],"chunking":[173],"alone.":[174]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-01-28T00:00:00"}