{"id":"https://openalex.org/W7224767274","doi":"https://doi.org/10.48550/arxiv.2610.39927","title":"Learning Calibrated Confidence for Multi-Agent Collaboration","display_name":"Learning Calibrated Confidence for Multi-Agent Collaboration","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224767274","doi":"https://doi.org/10.48550/arxiv.2610.39927"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39927","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39927","pdf_url":"https://arxiv.org/pdf/2610.39927","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.39927","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084334472","display_name":"Chenxiao Fan","orcid":"https://orcid.org/0009-0009-2509-7092","observed_orcids":["https://orcid.org/0009-0009-2509-7092","https://orcid.org/0009-0002-7090-2504"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan, Chenxiao","raw_affiliation_strings":["Qwen Business Unit of Alibaba","University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Business Unit of Alibaba","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160208143","display_name":"Chongming Gao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao, Chongming","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002460793","display_name":"Gangyi Zhang","orcid":"https://orcid.org/0009-0007-4092-993X","observed_orcids":["https://orcid.org/0009-0007-4092-993X","https://orcid.org/0009-0007-4865-9698"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Gangyi","raw_affiliation_strings":["Qwen Business Unit of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Business Unit of Alibaba","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102351435","display_name":"Yaxin Gong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gong, Yaxin","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104201792","display_name":"Leyang Shen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shen, Leyang","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160162025","display_name":"Jiakai Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Jiakai","raw_affiliation_strings":["Qwen Business Unit of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Business Unit of Alibaba","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160175416","display_name":"Dong Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Dong","raw_affiliation_strings":["Qwen Business Unit of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Business Unit of Alibaba","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160238743","display_name":"Yang Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Yang","raw_affiliation_strings":["Qwen Business Unit of Alibaba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qwen Business Unit of Alibaba","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160217787","display_name":"Haoyan Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Haoyan","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160170148","display_name":"Xinting Hu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu, Xinting","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051925942","display_name":"Fuli Feng","orcid":"https://orcid.org/0000-0002-5828-9842","observed_orcids":["https://orcid.org/0000-0002-5828-9842"]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng, Fuli","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160222302","display_name":"Xiangnan He","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He, Xiangnan","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.43070000410079956,"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":0.43070000410079956,"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":0.2184000015258789,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.04149999842047691,"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/multi-agent-systems","display_name":"multi-agent systems","score":0.7319999933242798},{"id":"https://openalex.org/keywords/confidence-calibration","display_name":"confidence calibration","score":0.9419999718666077},{"id":"https://openalex.org/keywords/multi-hop-question-answering","display_name":"multi-hop question answering","score":0.8889999985694885},{"id":"https://openalex.org/keywords/agent-cooperation","display_name":"agent cooperation","score":0.6399999856948853},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5630000233650208},{"id":"https://openalex.org/keywords/evidence-based-reasoning","display_name":"evidence-based reasoning","score":0.39100000262260437}],"concepts":[{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.8600000143051147},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7749999761581421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7656000256538391},{"id":"https://openalex.org/C191172861","wikidata":"https://www.wikidata.org/wiki/Q7899321","display_name":"Upstream (networking)","level":2,"score":0.7124999761581421},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7001000046730042},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5536999702453613},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5353999733924866},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46970000863075256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4357999861240387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4293000102043152},{"id":"https://openalex.org/C158980903","wikidata":"https://www.wikidata.org/wiki/Q7899329","display_name":"Upstream and downstream (DNA)","level":3,"score":0.4075999855995178},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3822000026702881},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3452000021934509},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C155108698","wikidata":"https://www.wikidata.org/wiki/Q1231081","display_name":"Randomized experiment","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2809000015258789},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39927","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39927","pdf_url":"https://arxiv.org/pdf/2610.39927","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.2610.39927","doi":"https://doi.org/10.48550/arxiv.2610.39927","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39927","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:2610.39927","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39927","pdf_url":"https://arxiv.org/pdf/2610.39927","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224767274.pdf","grobid_xml":"https://content.openalex.org/works/W7224767274.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7140841187","https://openalex.org/W7164592929","https://openalex.org/W7220995676","https://openalex.org/W7208763684","https://openalex.org/W2148242425","https://openalex.org/W7206178088","https://openalex.org/W7216239317","https://openalex.org/W7223845581","https://openalex.org/W2179878826","https://openalex.org/W7163013643"],"abstract_inverted_index":{"Complex":[0],"information":[1],"seeking":[2],"on":[3,78],"the":[4,63,79,110,119,129,138,141,146,161,168,173,183,226],"Web":[5,190],"often":[6],"requires":[7],"collecting":[8],"evidence":[9,41],"from":[10,177],"multiple":[11],"documents":[12],"and":[13,39,53,104,128,192,199,205,211,225,233],"reasoning":[14,193],"across":[15],"them,":[16],"as":[17],"in":[18,51,107,149],"multi-hop":[19],"question":[20],"answering.":[21],"Multi-agent":[22],"systems":[23,55],"address":[24],"such":[25],"tasks":[26],"by":[27,99],"dividing":[28],"work":[29],"among":[30],"specialized":[31],"agents,":[32,204],"where":[33,179],"upstream":[34,48,111,169,219],"agents":[35,44],"produce":[36,92],"intermediate":[37],"answers":[38,49],"supporting":[40],"that":[42,172,218],"downstream":[43,64,120,147,222],"build":[45],"upon.":[46],"However,":[47],"vary":[50],"correctness,":[52],"most":[54],"provide":[56],"no":[57],"quantitative":[58,123],"signal":[59,152],"about":[60],"it,":[61],"leaving":[62],"agent":[65,89,112,121,148,174],"to":[66,69,91,167,207],"judge":[67],"whether":[68],"trust":[70],"or":[71],"verify":[72],"what":[73],"it":[74,180],"receives":[75],"based":[76],"solely":[77],"textual":[80],"evidence.":[81],"In":[82],"this":[83,114,151],"paper,":[84],"we":[85,155],"propose":[86],"MASCAL.":[87],"Each":[88],"learns":[90,175],"a":[93,122,134],"correctness":[94],"probability":[95,115],"for":[96,125,202],"its":[97,126],"answer":[98,131],"jointly":[100],"optimizing":[101],"task":[102,197],"performance":[103],"confidence":[105,220,229],"calibration":[106,200],"reinforcement":[108],"learning;":[109],"passes":[113],"at":[116,164],"handoff,":[117],"giving":[118],"basis":[124],"decisions,":[127],"final":[130,228],"also":[132],"carries":[133],"calibrated":[135],"probability,":[136,170],"quantifying":[137],"reliability":[139],"of":[140],"system":[142],"output.":[143],"To":[144],"guide":[145],"using":[150],"during":[153],"training,":[154],"introduce":[156],"confidence-aware":[157],"weighting,":[158],"which":[159],"increases":[160],"learning":[162],"weight":[163],"positions":[165],"responsive":[166],"so":[171],"more":[176],"decisions":[178],"actively":[181],"uses":[182],"signal.":[184],"Across":[185],"three":[186],"collaboration":[187,209],"architectures":[188],"spanning":[189],"retrieval":[191],"tasks,":[194],"MASCAL":[195],"improves":[196],"accuracy":[198],"quality":[201],"both":[203],"generalizes":[206],"deeper":[208],"chains":[210],"different":[212],"model":[213],"scales.":[214],"Intervention":[215],"analysis":[216],"confirms":[217],"affects":[221],"decision":[223],"behavior,":[224],"learned":[227],"supports":[230],"selective":[231],"answering":[232],"targeted":[234],"rechecking.":[235]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-10-31T00:00:00"}
