{"id":"https://openalex.org/W4412875463","doi":"https://doi.org/10.1145/3711896.3736835","title":"Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning","display_name":"Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412875463","doi":"https://doi.org/10.1145/3711896.3736835"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3736835","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736835","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3736835","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3736835","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101672534","display_name":"Zhiyuan Ma","orcid":"https://orcid.org/0009-0003-9188-7275"},"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":true,"raw_author_name":"Zhiyuan Ma","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030410270","display_name":"Jiayu Liu","orcid":"https://orcid.org/0000-0001-8639-3308"},"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":"Jiayu Liu","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043503769","display_name":"X. L. Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianzhen Luo","raw_affiliation_strings":["Research Center for Social Computing and Interactive Robotics, Harbin Institute of Techology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Techology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085496384","display_name":"Zhenya Huang","orcid":"https://orcid.org/0000-0003-1661-0420"},"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":"Zhenya Huang","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041570266","display_name":"Qingfu Zhu","orcid":"https://orcid.org/0000-0003-3395-222X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingfu Zhu","raw_affiliation_strings":["Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019108029","display_name":"Wanxiang Che","orcid":"https://orcid.org/0000-0002-3907-0335"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanxiang Che","raw_affiliation_strings":["Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101672534"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":4.9698,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95117996,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2078","last_page":"2089"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9851999878883362,"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":0.9851999878883362,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9757999777793884,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.92330002784729,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7395991086959839},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.6945428848266602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40233364701271057},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3926488161087036},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.25489383935928345}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7395991086959839},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.6945428848266602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40233364701271057},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3926488161087036},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25489383935928345}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3711896.3736835","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736835","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3736835","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.04625","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.04625","pdf_url":"https://arxiv.org/pdf/2506.04625","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"doi:10.1145/3711896.3736835","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3711896.3736835","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3711896.3736835","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2347697912","display_name":null,"funder_award_id":"WK2150110038","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2802911279","display_name":null,"funder_award_id":"Young","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6013138505","display_name":null,"funder_award_id":"21501100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6770163833","display_name":null,"funder_award_id":"2308085Q","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"},{"id":"https://openalex.org/G6991849872","display_name":null,"funder_award_id":"62477044","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7033253288","display_name":null,"funder_award_id":"Grants","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8714109953","display_name":null,"funder_award_id":"QNRC001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8951484681","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412875463.pdf","grobid_xml":"https://content.openalex.org/works/W4412875463.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2075780421","https://openalex.org/W2990138404","https://openalex.org/W3129831491","https://openalex.org/W4320165837","https://openalex.org/W4385568260","https://openalex.org/W4389519928","https://openalex.org/W4392247224","https://openalex.org/W4394994587","https://openalex.org/W4396757449","https://openalex.org/W4396886508","https://openalex.org/W4396945188","https://openalex.org/W4400910426","https://openalex.org/W4401024948","https://openalex.org/W4401042981","https://openalex.org/W4401857375","https://openalex.org/W4401863329","https://openalex.org/W4401863346","https://openalex.org/W4401864065","https://openalex.org/W4402667093","https://openalex.org/W4402670152","https://openalex.org/W4402671878","https://openalex.org/W4404594861","https://openalex.org/W4404782665","https://openalex.org/W4404782902","https://openalex.org/W4404783749","https://openalex.org/W4404783916","https://openalex.org/W4404792814","https://openalex.org/W4406892424","https://openalex.org/W4409047968","https://openalex.org/W4409362584","https://openalex.org/W4409657210","https://openalex.org/W6817713987"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Empowering":[0],"large":[1],"language":[2],"models":[3,22],"(LLMs)":[4],"with":[5,199],"effective":[6],"tool":[7,29,46,115,128,133,157,220],"utilization":[8],"capabilities":[9,130,202],"is":[10],"crucial":[11],"for":[12],"enabling":[13],"AI":[14],"agents":[15],"to":[16,34,101,218],"solve":[17],"complex":[18],"problems.":[19],"However,":[20],"current":[21],"face":[23],"two":[24,80],"major":[25],"limitations:":[26],"(1)":[27],"unreliable":[28,114],"planning":[30,116],"and":[31,43,98,117,151,172,189,206],"invocation":[32],"due":[33],"low-quality":[35],"instruction":[36,107],"datasets":[37],"(e.g.,":[38,167],"widespread":[39],"hallucinated":[40],"API":[41,195],"calls),":[42],"(2)":[44],"weak":[45],"reflection":[47,129,148,221],"abilities":[48],"(over":[49],"90%":[50],"of":[51,113],"errors":[52],"cannot":[53],"be":[54],"corrected)":[55],"resulting":[56,145],"from":[57],"static":[58],"imitation":[59],"learning.":[60],"To":[61],"address":[62],"these":[63],"critical":[64,154],"limitations,":[65],"we":[66,84,120,160],"propose":[67,121],"Tool-MVR,":[68],"a":[69,90,104,136,225],"novel":[70],"Tool-Augmented":[71],"LLM":[72],"that":[73,93,109,177],"achieves":[74,179,224],"comprehensive":[75],"System":[76],"2":[77],"reasoning":[78,99],"through":[79,135],"key":[81],"innovations.":[82],"Specifically,":[83],"first":[85,214],"introduce":[86],"Multi-Agent":[87],"Meta-Verification":[88],"(MAMV),":[89],"systematic":[91],"pipeline":[92],"rigorously":[94],"validates":[95],"APIs,":[96],"queries,":[97],"trajectories":[100],"construct":[102],"ToolBench-V,":[103],"new":[105],"high-quality":[106],"dataset":[108,149],"addresses":[110],"the":[111,153,213],"limitation":[112],"invocation.":[118],"Second,":[119],"Exploration-based":[122],"Reflection":[123,140],"Learning":[124],"(EXPLORE),":[125],"which":[126],"enhances":[127],"by":[131,163,197],"leveraging":[132],"feedback":[134],"dynamic":[137],"\"Error":[138],"\u2192":[139,141],"Correction\"":[142],"learning":[143],"paradigm,":[144],"in":[146,156],"our":[147,210],"ToolBench-R":[150],"addressing":[152],"weakness":[155],"reflection.":[158],"Finally,":[159],"obtain":[161],"Tool-MVR":[162,178,223],"finetuning":[164],"open-source":[165],"LLMs":[166],"Qwen-7B)":[168],"on":[169,182,209],"both":[170,185],"ToolBench-V":[171],"ToolBench-R.":[173],"Our":[174],"experiments":[175],"demonstrate":[176],"state-of-the-art":[180],"performance":[181],"StableToolBench,":[183],"surpassing":[184],"ToolLLM":[186],"(by":[187,191],"23.9%)":[188],"GPT-4":[190],"15.3%)":[192],"while":[193],"reducing":[194],"calls":[196],"31.4%,":[198],"strong":[200],"generalization":[201],"across":[203],"unseen":[204],"tools":[205],"scenarios.":[207],"Additionally,":[208],"proposed":[211],"RefineToolBench,":[212],"benchmark":[215],"specifically":[216],"designed":[217],"evaluate":[219],"capabilities.":[222],"58.9%":[226],"error":[227],"correction":[228],"rate,":[229],"significantly":[230],"outperforming":[231],"ToolLLM's":[232],"9.1%.":[233]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}