{"id":"https://openalex.org/W4414360997","doi":"https://doi.org/10.24963/ijcai.2025/14","title":"MIRROR: Multi-agent Intra- and Inter-Reflection for Optimized Reasoning in Tool Learning","display_name":"MIRROR: Multi-agent Intra- and Inter-Reflection for Optimized Reasoning in Tool Learning","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360997","doi":"https://doi.org/10.24963/ijcai.2025/14"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/14","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/14","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104169594","display_name":"Zikang Guo","orcid":null},"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":"Zikang Guo","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/A5085563247","display_name":"Benfeng Xu","orcid":"https://orcid.org/0000-0003-0976-1634"},"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":"Benfeng Xu","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/A5100658019","display_name":"Xiaorui Wang","orcid":"https://orcid.org/0000-0001-9633-1418"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaorui Wang","raw_affiliation_strings":["Metastone Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Metastone Technology, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023341829","display_name":"Zhendong Mao","orcid":"https://orcid.org/0000-0001-5739-8126"},"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":"Zhendong Mao","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":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11907656,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"117","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9887999892234802,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9887999892234802,"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/T10703","display_name":"Business Process Modeling and Analysis","score":0.9498999714851379,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.947700023651123,"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/reflection","display_name":"Reflection (computer programming)","score":0.7529000043869019},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7081999778747559},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6944000124931335},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.6371999979019165},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6201000213623047},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4449999928474426},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3700999915599823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7615000009536743},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.7529000043869019},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7081999778747559},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6944000124931335},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6371999979019165},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6201000213623047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4772000014781952},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3953000009059906},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34380000829696655},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.32339999079704285},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29280000925064087},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2736999988555908},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.2524999976158142},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/14","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/14","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"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":{"Complex":[0],"tasks":[1],"involving":[2],"tool":[3],"integration":[4],"pose":[5],"significant":[6],"challenges":[7],"for":[8,31],"Large":[9],"Language":[10],"Models":[11],"(LLMs),":[12],"leading":[13],"to":[14,88,139,166],"the":[15,46,50,53,70,90,95,100,127,153],"emergence":[16],"of":[17,97,112],"multi-agent":[18],"workflows":[19],"as":[20,27],"a":[21,84,108,146],"promising":[22],"solution.":[23],"Reflection":[24],"has":[25],"emerged":[26],"an":[28],"effective":[29],"strategy":[30],"correcting":[32],"erroneous":[33,143],"trajectories":[34],"in":[35,45,65],"agentic":[36],"workflows.":[37],"However,":[38],"existing":[39,167],"approaches":[40],"only":[41,82],"exploit":[42],"such":[43],"capability":[44],"post-action":[47],"stage,":[48],"where":[49],"agent":[51,71],"observes":[52],"execution":[54],"outcomes.":[55],"We":[56],"argue":[57],"that,":[58],"like":[59],"humans,":[60],"LLMs":[61],"can":[62,72],"also":[63,93],"engage":[64],"reflection":[66,137],"before":[67,120],"action":[68],"execution:":[69],"anticipate":[73],"undesirable":[74],"outcomes":[75],"from":[76],"its":[77],"own":[78],"decisions,":[79],"which":[80,115,124],"not":[81],"provides":[83],"necessarily":[85],"complementary":[86],"perspective":[87],"evaluate":[89],"decision":[91],"but":[92],"prevents":[94],"propagation":[96],"errors":[98],"throughout":[99],"trajectory.":[101],"In":[102],"this":[103],"paper,":[104],"we":[105],"propose":[106],"MIRROR,":[107],"framework":[109],"that":[110],"consists":[111],"both":[113,152],"intra-reflection,":[114],"critically":[116],"assesses":[117],"intended":[118],"actions":[119,144],"execution,":[121],"and":[122,141,155],"inter-reflection,":[123],"further":[125],"adjusts":[126],"trajectory":[128],"based":[129],"on":[130,145,151],"observations.":[131],"This":[132],"design":[133],"systematically":[134],"leverages":[135],"LLM":[136],"capabilities":[138],"eliminate":[140],"rectify":[142],"more":[147],"comprehensive":[148],"scope.":[149],"Evaluations":[150],"StableToolBench":[154],"TravelPlanner":[156],"benchmarks":[157],"demonstrate":[158],"MIRROR's":[159],"superior":[160],"performance,":[161],"achieving":[162],"state-of-the-art":[163],"results":[164],"compared":[165],"approaches.":[168]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}