{"id":"https://openalex.org/W7166888317","doi":"https://doi.org/10.18653/v1/2026.acl-long.549","title":"MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching","display_name":"MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166888317","doi":"https://doi.org/10.18653/v1/2026.acl-long.549"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.549","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.549","pdf_url":"https://aclanthology.org/2026.acl-long.549.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.549.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139795183","display_name":"Changle Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changle Qu","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China ;","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139774793","display_name":"Sunhao Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sunhao Dai","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China ;","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139810922","display_name":"Hengyi Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengyi Cai","raw_affiliation_strings":["Baidu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139763963","display_name":"Jun Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xu","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China ;","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139779740","display_name":"Shuaiqiang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuaiqiang Wang","raw_affiliation_strings":["Baidu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139780934","display_name":"Dawei Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Yin","raw_affiliation_strings":["Baidu Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baidu Inc","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84985134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11953","last_page":"11968"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.12430000305175781,"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":0.12430000305175781,"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":0.11429999768733978,"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/T10028","display_name":"Topic Modeling","score":0.10679999738931656,"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/matching","display_name":"Matching (statistics)","score":0.5343000292778015},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.48980000615119934},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.26969999074935913},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.25029999017715454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5601999759674072},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5343000292778015},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.48980000615119934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4471000134944916},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40610000491142273},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33489999175071716},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3107999861240387},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25029999017715454},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.24889999628067017}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.549","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.549","pdf_url":"https://aclanthology.org/2026.acl-long.549.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.549","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.549","pdf_url":"https://aclanthology.org/2026.acl-long.549.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1862639538","display_name":null,"funder_award_id":"2023YFA1008704","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5643227726","display_name":null,"funder_award_id":"62472426","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G986537704","display_name":null,"funder_award_id":"62276248","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166888317.pdf","grobid_xml":"https://content.openalex.org/works/W7166888317.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tool-Integrated":[0],"Reasoning":[1],"(TIR)":[2],"empowers":[3],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"to":[8,33,43,97,102,128],"tackle":[9],"complex":[10],"tasks":[11],"by":[12],"interleaving":[13],"reasoning":[14],"steps":[15,35],"with":[16,107],"external":[17],"tool":[18,46],"interactions.However,":[19],"existing":[20],"reinforcement":[21],"learning":[22],"methods":[23],"typically":[24],"rely":[25],"on":[26,133],"outcome-or":[27],"trajectory-level":[28,122],"rewards,":[29],"assigning":[30,124],"uniform":[31],"advantages":[32],"all":[34],"within":[36],"a":[37,63,84,113],"trajectory.This":[38],"coarse-grained":[39],"credit":[40,81],"assignment":[41,74,82,95],"fails":[42],"distinguish":[44],"effective":[45],"calls":[47],"from":[48],"redundant":[49],"or":[50],"erroneous":[51],"ones,":[52],"particularly":[53,150],"in":[54,151],"long-horizon":[55,152],"multi-turn":[56],"scenarios.To":[57],"address":[58],"this,":[59],"we":[60,79,111],"propose":[61],"MatchTIR,":[62],"framework":[64],"that":[65,118],"introduces":[66],"fine-grained":[67],"supervision":[68],"via":[69],"bipartite":[70,85],"matching-based":[71],"turn-level":[72,100,120],"reward":[73],"and":[75,90,121,153],"dual-level":[76,114],"advantage":[77,115,126],"estimation.Specifically,":[78],"formulate":[80],"as":[83],"matching":[86],"problem":[87],"between":[88],"predicted":[89],"ground-truth":[91],"traces,":[92],"utilizing":[93],"two":[94],"strategies":[96],"derive":[98],"dense":[99],"rewards.Furthermore,":[101],"balance":[103],"local":[104],"step":[105],"precision":[106],"global":[108],"task":[109],"success,":[110],"introduce":[112],"estimation":[116],"scheme":[117],"integrates":[119],"signals,":[123],"distinct":[125],"values":[127],"individual":[129],"interaction":[130],"turns.Extensive":[131],"experiments":[132],"three":[134],"benchmarks":[135],"demonstrate":[136],"the":[137,145],"superiority":[138],"of":[139,147],"MatchTIR.Notably,":[140],"our":[141],"4B":[142],"model":[143],"surpasses":[144],"majority":[146],"8B":[148],"competitors,":[149],"multiturn":[154],"tasks.Our":[155],"codes":[156],"are":[157],"available":[158],"at":[159],"https:":[160],"//github.com/quchangle1/MatchTIR.":[161]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-07-02T00:00:00"}