{"id":"https://openalex.org/W7160949450","doi":"https://doi.org/10.48550/arxiv.2605.10082","title":"FERA: Uncertainty-Aware Federated Reasoning for Large Language Models","display_name":"FERA: Uncertainty-Aware Federated Reasoning for Large Language Models","publication_year":2026,"publication_date":"2026-05-11","ids":{"openalex":"https://openalex.org/W7160949450","doi":"https://doi.org/10.48550/arxiv.2605.10082"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.10082","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10082","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.2605.10082","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075287872","display_name":"Ruhan Wang","orcid":"https://orcid.org/0000-0001-5874-4350"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ruhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135976314","display_name":"Chengkai Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Chengkai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136000591","display_name":"Zhiyong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhiyong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135912183","display_name":"Junda Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Junda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135965261","display_name":"Rui Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135943454","display_name":"Tong Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135992211","display_name":"Julian McAuley","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"McAuley, Julian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135912223","display_name":"Lina Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Lina","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135920264","display_name":"Dongruo Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Dongruo","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/T11273","display_name":"Advanced Graph Neural Networks","score":0.12269999831914902,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.12269999831914902,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.10450000315904617,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.09470000118017197,"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/context","display_name":"Context (archaeology)","score":0.6098999977111816},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5845000147819519},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.5741999745368958},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5717999935150146},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.5156000256538391},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5145999789237976},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.4406000077724457},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.42570000886917114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8349000215530396},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6098999977111816},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5845000147819519},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5741999745368958},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5717999935150146},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.5156000256538391},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5145999789237976},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.4406000077724457},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3587999939918518},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.3125},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C12269588","wikidata":"https://www.wikidata.org/wiki/Q132364","display_name":"Communications protocol","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27309998869895935},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2709999978542328},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27070000767707825},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C158156997","wikidata":"https://www.wikidata.org/wiki/Q1416645","display_name":"Models of communication","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2623000144958496},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.10082","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10082","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.2605.10082","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.10082","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":[{"score":0.44696885347366333,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"exhibit":[4],"strong":[5],"reasoning":[6,41,101,114,162,188],"capabilities":[7],"when":[8],"guided":[9],"by":[10,42],"high-quality":[11],"demonstrations,":[12,49],"yet":[13],"such":[14],"data":[15,55,72],"is":[16,60,64,116],"often":[17],"distributed":[18],"across":[19,205],"organizations":[20],"that":[21,61,115,173,180,191],"cannot":[22,69],"centralize":[23],"it":[24],"due":[25],"to":[26,73,164],"regulatory,":[27],"proprietary,":[28],"or":[29,53],"institutional":[30],"constraints.":[31],"We":[32,168],"study":[33],"federated":[34,196],"reasoning,":[35],"where":[36],"a":[37,88],"server":[38,68,109,127],"improves":[39],"multi-step":[40],"coordinating":[43],"with":[44,103],"heterogeneous":[45,142],"clients":[46,99],"holding":[47],"private":[48],"without":[50],"centralized":[51],"training":[52,197],"raw":[54],"sharing.":[56],"The":[57],"key":[58],"challenge":[59],"client":[62,71,143],"reliability":[63],"query-dependent,":[65],"while":[66,207],"the":[67,108,121,174],"inspect":[70],"determine":[74],"which":[75],"contributions":[76],"are":[77],"trustworthy.":[78],"To":[79],"address":[80],"this,":[81],"we":[82],"propose":[83],"Uncertainty-Aware":[84,135],"Federated":[85],"Reasoning":[86],"(FERA),":[87],"training-free":[89,199],"framework":[90],"based":[91],"on":[92,186],"iterative":[93,176],"server-client":[94],"co-refinement.":[95],"Across":[96],"communication":[97,209],"rounds,":[98],"generate":[100],"traces":[102,144],"lightweight":[104],"uncertainty":[105],"estimates,":[106],"and":[107,129,149,179,198,210],"synthesizes":[110],"them":[111],"into":[112],"improved":[113],"redistributed":[117],"as":[118],"context":[119],"for":[120],"next":[122],"round,":[123,134],"progressively":[124,202],"improving":[125],"both":[126,195],"outputs":[128],"client-side":[130],"reasoning.":[131],"Within":[132],"each":[133],"Self-Critique":[136],"Aggregation":[137],"(UA-SCA)":[138],"resolves":[139],"conflicts":[140],"among":[141],"through":[145],"query-dependent":[146],"trust":[147],"weighting":[148,182],"structured":[150],"cross-client":[151],"verification.":[152],"Rather":[153],"than":[154],"simply":[155],"discarding":[156],"low-quality":[157],"traces,":[158],"UA-SCA":[159],"revises":[160],"flawed":[161],"steps":[163],"recover":[165],"useful":[166],"information.":[167],"provide":[169],"theoretical":[170],"guarantees":[171],"showing":[172],"proposed":[175],"protocol":[177],"converges":[178],"uncertainty-aware":[181],"accelerates":[183],"convergence.":[184],"Experiments":[185],"multiple":[187],"benchmarks":[189],"show":[190],"FERA":[192],"consistently":[193],"outperforms":[194],"baselines,":[200],"achieving":[201],"higher":[203],"accuracy":[204],"rounds":[206],"maintaining":[208],"computational":[211],"efficiency.":[212]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-13T00:00:00"}