{"id":"https://openalex.org/W7129080004","doi":"https://doi.org/10.1145/3773966.3777952","title":"TOOL-CURE: Tool Selection via Curriculum-Enhanced Reinforcement Learning with Sample Screening for LLMs","display_name":"TOOL-CURE: Tool Selection via Curriculum-Enhanced Reinforcement Learning with Sample Screening for LLMs","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129080004","doi":"https://doi.org/10.1145/3773966.3777952"},"language":null,"primary_location":{"id":"doi:10.1145/3773966.3777952","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777952","pdf_url":null,"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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3773966.3777952","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126116870","display_name":"Jie Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126130871","display_name":"Dongsheng Bi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongsheng Bi","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126137030","display_name":"Tao Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Sun","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126087726","display_name":"Minghui Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minghui Yang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126119562","display_name":"Jian Ming Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Wang","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100633632","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0003-0098-5359"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwei Wang","raw_affiliation_strings":["Huazhong University of Science and Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5126116870"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79922196,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"946","last_page":"954"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.3111000061035156,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.3111000061035156,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.10909999907016754,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.08129999786615372,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7067999839782715},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6805999875068665},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5371000170707703},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5249000191688538},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4878000020980835},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.46700000762939453},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.43309998512268066},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.3880999982357025}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7067999839782715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6822999715805054},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6805999875068665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6579999923706055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6290000081062317},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5249000191688538},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4878000020980835},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.46700000762939453},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.3880999982357025},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3231000006198883},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.30820000171661377},{"id":"https://openalex.org/C2778583558","wikidata":"https://www.wikidata.org/wiki/Q771245","display_name":"Code reuse","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3773966.3777952","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777952","pdf_url":null,"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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3773966.3777952","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777952","pdf_url":null,"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 Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5799611806869507,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W4393065402"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"deployed":[6],"as":[7,83,93],"intelligent":[8],"agents":[9],"capable":[10],"of":[11,31,64,97],"executing":[12],"complex":[13],"real-world":[14,32,219],"tasks":[15],"through":[16,120],"external":[17],"tool":[18,22,40],"interactions,":[19],"but":[20],"effective":[21],"selection":[23],"remains":[24],"challenging":[25],"due":[26,135],"to":[27,103,136,160,182,202],"the":[28,62,101],"inherent":[29],"limitations":[30],"training":[33,133,168],"data.":[34],"These":[35],"datasets":[36],"suffer":[37,131],"from":[38,132,143,206,217],"severe":[39],"imbalance":[41],"following":[42],"long-tail":[43],"distributions,":[44],"data":[45],"scarcity":[46],"for":[47],"specialized":[48],"tools,":[49,57],"logic":[50],"conflicts":[51],"between":[52],"user":[53],"queries":[54],"and":[55,61,70,99,140,185,198,214,233],"available":[56,239],"rapidly":[58],"evolving":[59],"toolsets,":[60],"presence":[63],"subpar":[65],"samples":[66,179,201],"including":[67],"partially":[68],"correct":[69],"dirty":[71,200],"examples.":[72],"Existing":[73],"supervised":[74],"fine-tuning":[75],"(SFT)":[76],"approaches":[77,124],"struggle":[78],"with":[79,156],"these":[80,148],"multifaceted":[81],"challenges":[82],"they":[84],"require":[85],"abundant":[86],"high-quality":[87],"data,":[88,220],"treat":[89],"all":[90],"labeled":[91],"examples":[92],"ground":[94],"truth":[95],"regardless":[96],"quality,":[98],"lack":[100],"flexibility":[102],"generalize":[104],"beyond":[105],"specific":[106],"query-tool":[107],"pairings":[108],"seen":[109],"during":[110],"training.":[111],"While":[112],"reinforcement":[113],"learning":[114,142,216],"(RL)":[115],"offers":[116],"a":[117,153,170,223],"promising":[118],"alternative":[119],"outcome-based":[121],"learning,":[122],"vanilla":[123],"like":[125],"Group":[126],"Relative":[127],"Policy":[128,187],"Optimization":[129],"(GRPO)":[130],"instability":[134],"conflicting":[137],"reward":[138],"signals":[139],"inefficient":[141],"weak":[144],"signals.":[145],"To":[146],"address":[147],"issues,":[149],"we":[150],"propose":[151],"TOOL-CURE,":[152],"novel":[154],"method":[155],"two":[157],"key":[158],"improvements":[159,230],"GRPO:":[161],"Proficiency-Scaled":[162],"Curriculum":[163],"Learning":[164],"(PSCL),":[165],"which":[166,193],"organizes":[167],"into":[169],"two-stage":[171],"curriculum":[172],"that":[173,227],"builds":[174],"foundational":[175],"skills":[176],"on":[177],"easier":[178],"before":[180],"progressing":[181],"harder":[183],"ones,":[184],"Online":[186],"Guarding":[188],"via":[189],"Sample":[190],"Screening":[191],"(OPGSS),":[192],"continuously":[194],"assesses":[195],"rollout":[196],"quality":[197],"masks":[199],"prevent":[203],"noisy":[204],"gradients":[205],"destabilizing":[207],"policy":[208],"updates.":[209],"Our":[210,236],"approach":[211],"enables":[212],"stable":[213],"efficient":[215],"heterogeneous":[218],"resulting":[221],"in":[222,231],"robust":[224],"tool-selection":[225],"agent":[226],"demonstrates":[228],"significant":[229],"accuracy":[232],"generalization":[234],"capability.":[235],"code":[237],"is":[238],"at:":[240],"https://github.com/einnullnull/TOOL-CURE.git.":[241]},"counts_by_year":[],"updated_date":"2026-02-18T06:20:13.636215","created_date":"2026-02-17T00:00:00"}