{"id":"https://openalex.org/W7166798706","doi":"https://doi.org/10.18653/v1/2026.findings-acl.419","title":"ToolRM: Towards Agentic Tool-Use Reward Modeling","display_name":"ToolRM: Towards Agentic Tool-Use Reward Modeling","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166798706","doi":"https://doi.org/10.18653/v1/2026.findings-acl.419"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.419","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.419","pdf_url":"https://aclanthology.org/2026.findings-acl.419.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.419.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139778344","display_name":"Renhao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Renhao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139827268","display_name":"Jianhong Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianhong Tu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139848931","display_name":"Yang Su","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Su","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139807851","display_name":"Yantao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yantao Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139745324","display_name":"Fei Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139726361","display_name":"Hamid Alinejad-Rokny","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hamid Alinejad-Rokny","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139722114","display_name":"Derek F. Wong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Derek F. Wong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139797305","display_name":"Junyang Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junyang Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139848164","display_name":"Min Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min Yang","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83872104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8613","last_page":"8640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.11969999969005585,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.11969999969005585,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.07500000298023224,"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/T12127","display_name":"Software System Performance and Reliability","score":0.05209999904036522,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/discriminative-model","display_name":"Discriminative model","score":0.7117000222206116},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6771000027656555},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5834000110626221},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5400000214576721},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.4846999943256378},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.45080000162124634},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.436599999666214},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4207000136375427}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7117000222206116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6886000037193298},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6771000027656555},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6043000221252441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5986999869346619},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5834000110626221},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5400000214576721},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4846999943256378},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.45080000162124634},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.436599999666214},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41909998655319214},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.2827000021934509},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C2779251273","wikidata":"https://www.wikidata.org/wiki/Q43436","display_name":"Pearl","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.26159998774528503}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.419","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.419","pdf_url":"https://aclanthology.org/2026.findings-acl.419.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.419","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.419","pdf_url":"https://aclanthology.org/2026.findings-acl.419.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4615181649","display_name":null,"funder_award_id":"62266013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4850745499","display_name":null,"funder_award_id":"2024A1515030166","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G5650156489","display_name":null,"funder_award_id":"2024YFF0908200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5893188460","display_name":null,"funder_award_id":"0007/2024/AKP","funder_id":"https://openalex.org/F4320323893","funder_display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia"},{"id":"https://openalex.org/G7310247692","display_name":null,"funder_award_id":"62376262","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320311133","display_name":"United Mitochondrial Disease Foundation","ror":"https://ror.org/0528q0t18"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320323893","display_name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia","ror":"https://ror.org/05vna4324"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166798706.pdf","grobid_xml":"https://content.openalex.org/works/W7166798706.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reward":[0],"models":[1,11,46,114],"(RMs)":[2],"play":[3],"a":[4,41,57,74,94],"critical":[5],"role":[6],"in":[7,16,131],"aligning":[8],"large":[9],"language":[10],"(LLMs)":[12],"with":[13],"human":[14],"preferences.Yet":[15],"the":[17,22,98,116],"domain":[18],"of":[19,24,43],"tool":[20,107],"learning,":[21],"lack":[23],"RMs":[25,105,130],"specifically":[26],"designed":[27],"for":[28,48,168],"function-calling":[29],"tasks":[30],"has":[31],"limited":[32],"progress":[33],"toward":[34],"more":[35],"capable":[36],"agentic":[37],"AI.We":[38],"introduce":[39,90],"TOOLRM,":[40],"family":[42],"lightweight":[44],"reward":[45,87,133],"tailored":[47],"general":[49],"tool-use":[50],"scenarios.To":[51],"build":[52],"these":[53],"models,":[54],"we":[55],"propose":[56],"novel":[58],"pipeline":[59],"that":[60,81],"constructs":[61],"high-quality":[62],"pairwise":[63,132],"preference":[64,79],"data":[65,178],"using":[66],"rule-based":[67],"scoring":[68],"and":[69,77,85,129,147,154],"multidimensional":[70],"sampling.This":[71],"yields":[72],"ToolPref-Pairwise-30K,":[73],"diverse,":[75],"balanced,":[76],"challenging":[78],"dataset":[80],"supports":[82],"both":[83],"generative":[84,137],"discriminative":[86],"modeling.We":[88],"also":[89],"TRBENCH":[91],"BFCL":[92,102],",":[93],"benchmark":[95],"built":[96],"on":[97,106,110,149],"agent":[99],"evaluation":[100],"suite":[101],"to":[103,121,140,179],"evaluate":[104],"calling":[108],"tasks.Trained":[109],"our":[111],"constructed":[112],"data,":[113],"from":[115],"Qwen3-4B/8B":[117],"series":[118],"achieve":[119],"up":[120],"17.94%":[122],"higher":[123],"accuracy,":[124],"substantially":[125],"outperforming":[126],"frontier":[127],"LLMs":[128],"judgments.Beyond":[134],"training":[135,171],"objectives,":[136],"ToolRM":[138],"generalizes":[139],"broader":[141],"critique":[142],"tasks,":[143],"including":[144],"Best-of-N":[145],"sampling":[146],"self-correction.Experiments":[148],"ACEBench":[150],"highlight":[151],"its":[152,174],"effectiveness":[153],"efficiency,":[155],"enabling":[156],"inference-time":[157],"scaling":[158],"while":[159],"reducing":[160],"output":[161],"token":[162],"usage":[163],"by":[164],"over":[165],"66%.Its":[166],"support":[167],"downstream":[169],"RL":[170],"further":[172],"validates":[173],"practical":[175],"utility.We":[176],"release":[177],"facilitate":[180],"future":[181],"research.":[182]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}