{"id":"https://openalex.org/W7224955813","doi":"https://doi.org/10.48550/arxiv.2610.39682","title":"Heterogeneous Co-Evolution Learning for Tool-Efficient Search Agents with Zero Labels","display_name":"Heterogeneous Co-Evolution Learning for Tool-Efficient Search Agents with Zero Labels","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224955813","doi":"https://doi.org/10.48550/arxiv.2610.39682"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39682","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39682","pdf_url":"https://arxiv.org/pdf/2610.39682","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/2610.39682","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5145903925","display_name":"Qin-Wen Luo","orcid":"https://orcid.org/0009-0005-9606-466X","observed_orcids":["https://orcid.org/0009-0005-9606-466X"]},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luo, Qin-Wen","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics , Nanjing , China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160154146","display_name":"Sheng Ren","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ren, Sheng","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics , Nanjing , China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160220589","display_name":"Xiang Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Xiang","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics , Nanjing , China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160193537","display_name":"Rui Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Rui","raw_affiliation_strings":["Didichuxing Co. Ltd , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Didichuxing Co. Ltd , Beijing , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160213198","display_name":"Jun Fang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Jun","raw_affiliation_strings":["Didichuxing Co. Ltd , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Didichuxing Co. Ltd , Beijing , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020921636","display_name":"Naiqiang Tan","orcid":"https://orcid.org/0009-0008-4687-5212","observed_orcids":["https://orcid.org/0009-0008-4687-5212"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Naiqiang","raw_affiliation_strings":["Didichuxing Co. Ltd , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Didichuxing Co. Ltd , Beijing , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160157475","display_name":"Jun Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jun","raw_affiliation_strings":["Didichuxing Co. Ltd , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Didichuxing Co. Ltd , Beijing , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160206121","display_name":"Hua Chai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chai, Hua","raw_affiliation_strings":["Didichuxing Co. Ltd , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Didichuxing Co. Ltd , Beijing , China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160202628","display_name":"Sheng-Jun Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Sheng-Jun","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics , Nanjing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics , Nanjing , China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.9345999956130981,"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":0.9345999956130981,"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":0.05040000006556511,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.003000000026077032,"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/search-agents","display_name":"search agents","score":0.8569999933242798},{"id":"https://openalex.org/keywords/tool-efficiency","display_name":"tool efficiency","score":0.6370000243186951},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.4350000023841858},{"id":"https://openalex.org/keywords/multi-hop-question-answering","display_name":"multi-hop question answering","score":0.6320000290870667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921000123023987},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7002999782562256},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.667900025844574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6315000057220459},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5494999885559082},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.5041000247001648},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3366999924182892},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C201789804","wikidata":"https://www.wikidata.org/wiki/Q2362762","display_name":"Search problem","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39682","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39682","pdf_url":"https://arxiv.org/pdf/2610.39682","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.2610.39682","doi":"https://doi.org/10.48550/arxiv.2610.39682","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39682","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:2610.39682","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39682","pdf_url":"https://arxiv.org/pdf/2610.39682","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/W7224955813.pdf","grobid_xml":"https://content.openalex.org/works/W7224955813.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W6884962196"],"related_works":["https://openalex.org/W7123926815","https://openalex.org/W4414972172","https://openalex.org/W7214898040","https://openalex.org/W7162694350","https://openalex.org/W7171646184","https://openalex.org/W4415194584","https://openalex.org/W7172390971","https://openalex.org/W7172406067","https://openalex.org/W7163906142","https://openalex.org/W7160432063"],"abstract_inverted_index":{"Deep":[0],"search":[1,100,138,193],"agents":[2,28,44],"extend":[3],"language":[4],"models":[5],"by":[6,32],"interleaving":[7],"reasoning":[8,128],"with":[9,162],"external":[10],"retrieval.":[11],"However,":[12],"effective":[13,209],"search-agent":[14,87,180,210],"training":[15,33,88,115],"requires":[16],"addressing":[17],"two":[18],"challenges":[19],"beyond":[20],"final-answer":[21],"optimization.":[22],"First,":[23],"the":[24,118,124,146,154],"capability":[25,121],"frontier":[26],"of":[27],"is":[29],"largely":[30],"determined":[31],"questions,":[34,96],"whereas":[35],"fixed":[36],"or":[37,191],"labeled":[38,188],"task":[39,135],"collections":[40],"cannot":[41],"adapt":[42],"as":[43],"improve.":[45],"Second,":[46],"outcome-only":[47],"reinforcement":[48,130],"learning":[49],"treats":[50],"all":[51],"successful":[52],"trajectories":[53],"equally,":[54],"even":[55],"when":[56],"some":[57],"correct":[58,160],"answers":[59,161],"rely":[60],"on":[61,167],"redundant":[62,164],"searches,":[63],"creating":[64],"an":[65,104,142],"inherent":[66],"tension":[67],"between":[68],"answer":[69],"accuracy":[70],"and":[71,83,106,137,148,159,170,204],"tool":[72,185],"efficiency.":[73],"To":[74,132],"address":[75],"these":[76],"issues,":[77],"we":[78],"introduce":[79],"\\textsc{ZEST-Search},":[80],"a":[81,149],"zero-label":[82],"tool-efficient":[84],"framework":[85],"for":[86,145,153],"via":[89],"heterogeneous":[90,111,199],"co-evolution.":[91],"Starting":[92],"from":[93],"unlabeled":[94],"reference":[95],"\\textsc{ZEST-Search}":[97,140,177],"constructs":[98,114],"validated":[99],"tasks":[101,116,158],"online":[102],"through":[103,129],"answer-first":[105],"evidence-path-guided":[107],"generation":[108],"process.":[109],"A":[110],"proposer":[112,147],"adaptively":[113],"around":[117],"solver's":[119],"evolving":[120],"boundary,":[122],"while":[123,182],"solver":[125],"learns":[126],"search-augmented":[127],"learning.":[131],"jointly":[133],"optimize":[134],"difficulty":[136,202],"efficiency,":[139],"employs":[141],"intermediate-difficulty":[143],"reward":[144,152],"task-local":[150],"tool-aware":[151,205],"solver,":[155],"encouraging":[156],"informative":[157],"fewer":[163],"searches.":[165],"Experiments":[166],"seven":[168],"general-domain":[169],"multi-hop":[171],"question":[172],"answering":[173],"benchmarks":[174],"demonstrate":[175],"that":[176,198],"consistently":[178],"improves":[179],"performance":[181],"achieving":[183],"higher":[184],"efficiency":[186],"without":[187],"search-training":[189],"data":[190],"expert":[192],"trajectories.":[194],"Further":[195],"analyses":[196],"show":[197],"generation,":[200],"adaptive":[201],"control,":[203],"optimization":[206],"enable":[207],"more":[208],"training.":[211]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-31T00:00:00"}