{"id":"https://openalex.org/W7133334122","doi":"https://doi.org/10.48550/arxiv.2603.01940","title":"CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification","display_name":"CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification","publication_year":2026,"publication_date":"2026-03-02","ids":{"openalex":"https://openalex.org/W7133334122","doi":"https://doi.org/10.48550/arxiv.2603.01940"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.01940","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01940","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.01940","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127956718","display_name":"Jinpeng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jinpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127964939","display_name":"Cheng Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gong, Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128015917","display_name":"Hanbo Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hanbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112922588","display_name":"Ziru Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Ziru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127953859","display_name":"Zichen Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Zichen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079648643","display_name":"Xinyu Fu","orcid":"https://orcid.org/0000-0002-3591-4158"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Xinyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101409340","display_name":"Shi Wu","orcid":"https://orcid.org/0000-0002-6842-7487"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127933401","display_name":"Chenyang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chenyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128000216","display_name":"Wu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074987017","display_name":"Suiyun Zhang","orcid":"https://orcid.org/0000-0002-3205-5896"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Suiyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128027931","display_name":"Dandan Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tu, Dandan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127959153","display_name":"Rui Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5634999871253967,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5634999871253967,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.12960000336170197,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.03539999946951866,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6851999759674072},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.649399995803833},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5730999708175659},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5566999912261963},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5266000032424927},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.526199996471405},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.49549999833106995},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4683000147342682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7804999947547913},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6851999759674072},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.649399995803833},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5730999708175659},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5566999912261963},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5537999868392944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5281000137329102},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5266000032424927},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.526199996471405},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.49549999833106995},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4683000147342682},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.45410001277923584},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3619999885559082},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2921999990940094},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C168074166","wikidata":"https://www.wikidata.org/wiki/Q31615","display_name":"Cove","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25769999623298645},{"id":"https://openalex.org/C2776716048","wikidata":"https://www.wikidata.org/wiki/Q6045290","display_name":"Interactive Learning","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.01940","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01940","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.01940","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01940","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.47807544469833374}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Developing":[0],"multi-turn":[1],"interactive":[2,41,171],"tool-use":[3,42,172],"agents":[4,17,43],"is":[5],"challenging":[6,106],"because":[7],"real-world":[8],"user":[9],"needs":[10],"are":[11],"often":[12],"complex":[13,68],"and":[14,49,70,91,125,130,144,162,184],"ambiguous,":[15],"yet":[16],"must":[18],"execute":[19],"deterministic":[20,73],"actions":[21],"to":[22,150],"satisfy":[23],"them.":[24],"To":[25,174],"address":[26],"this":[27],"gap,":[28],"we":[29,178],"introduce":[30],"\\textbf{CoVe}":[31],"(\\textbf{Co}nstraint-\\textbf{Ve}rification),":[32],"a":[33,60],"post-training":[34],"data":[35,47,168],"synthesis":[36],"framework":[37],"designed":[38],"for":[39,75,87,98,165,169,193],"training":[40,85,167],"while":[44],"ensuring":[45],"both":[46],"complexity":[48],"correctness.":[50],"CoVe":[51,158],"begins":[52],"by":[53],"defining":[54],"explicit":[55],"task":[56],"constraints,":[57],"which":[58],"serve":[59],"dual":[61],"role:":[62],"they":[63],"guide":[64],"the":[65,81,92,105,110,113,128,185],"generation":[66],"of":[67,83,94,112,123,141,188],"trajectories":[69,86,191],"act":[71],"as":[72],"verifiers":[74],"assessing":[76],"trajectory":[77],"quality.":[78],"This":[79],"enables":[80],"creation":[82],"high-quality":[84,190],"supervised":[88],"fine-tuning":[89],"(SFT)":[90],"derivation":[93],"accurate":[95],"reward":[96],"signals":[97],"reinforcement":[99],"learning":[100],"(RL).":[101],"Our":[102],"evaluation":[103],"on":[104],"$\u03c4^2$-bench":[107],"benchmark":[108],"demonstrates":[109],"effectiveness":[111],"framework.":[114],"Notably,":[115],"our":[116,180],"compact":[117],"\\textbf{CoVe-4B}":[118],"model":[119],"achieves":[120],"success":[121],"rates":[122],"43.0\\%":[124],"59.4\\%":[126],"in":[127],"Airline":[129],"Retail":[131],"domains,":[132],"respectively;":[133],"its":[134,152],"overall":[135],"performance":[136],"significantly":[137],"outperforms":[138],"strong":[139],"baselines":[140],"similar":[142],"scale":[143],"remains":[145],"competitive":[146],"with":[147],"models":[148],"up":[149],"$17\\times$":[151],"size.":[153],"These":[154],"results":[155],"indicate":[156],"that":[157],"provides":[159],"an":[160],"effective":[161],"efficient":[163],"pathway":[164],"synthesizing":[166],"state-of-the-art":[170],"agents.":[173],"support":[175],"future":[176],"research,":[177],"open-source":[179],"code,":[181],"trained":[182],"model,":[183],"full":[186],"set":[187],"12K":[189],"used":[192],"training.":[194]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-04T00:00:00"}