{"id":"https://openalex.org/W7214574604","doi":"https://doi.org/10.18653/2026.findings-emnlp.1132","title":"RecToolBench: Benchmarking Recommendation-Specific Tool Orchestration under Fuzzy User Intent","display_name":"RecToolBench: Benchmarking Recommendation-Specific Tool Orchestration under Fuzzy User Intent","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7214574604","doi":"https://doi.org/10.18653/2026.findings-emnlp.1132"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.1132","doi":"https://doi.org/10.18653/2026.findings-emnlp.1132","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1132","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1132.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.findings-emnlp.1132.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153313293","display_name":"Xiao Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiao Chen","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140333805","display_name":"Yicheng Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yicheng Zhao","raw_affiliation_strings":["Jilin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137564066","display_name":"Yingying Wu","orcid":"https://orcid.org/0009-0008-0448-2429","observed_orcids":["https://orcid.org/0009-0008-0448-2429"]},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingying Wu","raw_affiliation_strings":["Jilin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056167440","display_name":"Zhendong Chu","orcid":"https://orcid.org/0000-0002-5707-1112","observed_orcids":["https://orcid.org/0000-0002-5707-1112"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhendong Chu","raw_affiliation_strings":["Squirrel AI Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Squirrel AI Learning","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036449631","display_name":"Changyi Ma","orcid":"https://orcid.org/0000-0002-4617-5821","observed_orcids":["https://orcid.org/0000-0002-4617-5821"]},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyi Ma","raw_affiliation_strings":["Jilin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153357572","display_name":"Qingsong Wen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingsong Wen","raw_affiliation_strings":["Squirrel AI Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Squirrel AI Learning","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153249493","display_name":"Xuan Song","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Song","raw_affiliation_strings":["Jilin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jilin University","institution_ids":["https://openalex.org/I194450716"]}]}],"institutions":[],"countries_distinct_count":2,"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":0.69028616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23958","last_page":"23983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9961000084877014,"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":0.9961000084877014,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.002400000113993883,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":9.999999747378752e-05,"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/tool-orchestration","display_name":"tool orchestration","score":0.9580000042915344},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.6380000114440918},{"id":"https://openalex.org/keywords/model-context-protocol","display_name":"Model Context Protocol","score":0.8870000243186951},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.8180000185966492},{"id":"https://openalex.org/keywords/tool-chain","display_name":"toolchain","score":0.40299999713897705},{"id":"https://openalex.org/keywords/evidence-integration","display_name":"evidence integration","score":0.6510000228881836},{"id":"https://openalex.org/keywords/recommendation-evaluation","display_name":"recommendation evaluation","score":0.3499999940395355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8241999745368958},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.7972000241279602},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.7247999906539917},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.6718000173568726},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.661899983882904},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5182999968528748},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C33499554","wikidata":"https://www.wikidata.org/wiki/Q1417134","display_name":"Dashboard","level":2,"score":0.39149999618530273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35899999737739563},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33340001106262207},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32989999651908875},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3255999982357025},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32339999079704285},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2888000011444092},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27379998564720154},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C42011625","wikidata":"https://www.wikidata.org/wiki/Q1055058","display_name":"Fuzzy set","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.26510000228881836},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C28034677","wikidata":"https://www.wikidata.org/wiki/Q17092530","display_name":"Interleaving","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C2780150774","wikidata":"https://www.wikidata.org/wiki/Q252500","display_name":"User profile","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.1132","doi":"https://doi.org/10.18653/2026.findings-emnlp.1132","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1132","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1132.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2609.30717","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.30717","pdf_url":"https://arxiv.org/pdf/2609.30717","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.30717","doi":"https://doi.org/10.48550/arxiv.2609.30717","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.30717","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/2026.findings-emnlp.1132","doi":"https://doi.org/10.18653/2026.findings-emnlp.1132","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1132","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1132.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214574604.pdf","grobid_xml":"https://content.openalex.org/works/W7214574604.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W4297899430","https://openalex.org/W4399836817","https://openalex.org/W4406604156","https://openalex.org/W4415065819","https://openalex.org/W4415130727","https://openalex.org/W4417006854","https://openalex.org/W4417134740","https://openalex.org/W4417473560","https://openalex.org/W6891974623","https://openalex.org/W6892107230","https://openalex.org/W7102803052","https://openalex.org/W7134947108"],"related_works":["https://openalex.org/W7161831420","https://openalex.org/W6979359834","https://openalex.org/W7164154021","https://openalex.org/W7161050093","https://openalex.org/W7140188496","https://openalex.org/W6892107230","https://openalex.org/W7128731989","https://openalex.org/W7154397947","https://openalex.org/W4416365680","https://openalex.org/W7170179008"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"agentic":[3,165],"recommender":[4,8,61,166],"systems":[5,9],"are":[6,171],"shifting":[7],"from":[10],"passive":[11],"filtering":[12],"engines":[13],"to":[14,21],"instructionfollowing":[15],"agents":[16,62],"that":[17,103,125],"use":[18],"external":[19],"tools":[20],"resolve":[22],"user":[23,30,65,158],"intent.However,":[24],"existing":[25],"benchmarks":[26],"often":[27],"assume":[28],"explicit":[29],"intent,":[31],"simplified":[32],"tool":[33,41,87,90,94,128,154],"environments,":[34],"or":[35],"isolated":[36],"function":[37],"calls,":[38,85,88],"leaving":[39],"realistic":[40],"orchestration":[42,149,155],"for":[43,58,164],"recommendation":[44,75,107],"underexplored.To":[45],"bridge":[46],"this":[47],"gap,":[48],"we":[49],"propose":[50],"RecToolBench,":[51],"a":[52,99,161],"Model":[53],"Context":[54],"Protocol":[55],"(MCP)-based":[56],"benchmark":[57],"evaluating":[59],"tool-using":[60],"under":[63,156],"fuzzy":[64,106,157],"instructions.Rec-ToolBench":[66],"contains":[67],"more":[68],"than":[69],"1,200":[70],"executable":[71,105],"tasks":[72],"across":[73],"three":[74],"domains,":[76],"13":[77],"MCP":[78],"servers,":[79],"and":[80,92,109,117,143,169],"32":[81],"tools,":[82],"spanning":[83],"single-tool":[84],"parallel":[86],"sequential":[89],"chains,":[91],"hybrid":[93],"orchestration.We":[95],"construct":[96],"RecToolBench":[97],"with":[98,136],"scalable":[100],"synthesize-fuzzify-judge":[101],"pipeline":[102],"generates":[104],"tasks,":[108],"evaluates":[110],"agent":[111],"trajectories":[112],"using":[113],"rule-based":[114],"execution":[115],"checks":[116],"rubric-based":[118],"LLM":[119],"evaluation.Experiments":[120],"on":[121],"representative":[122],"LLMs":[123],"show":[124],"syntactically":[126],"valid":[127],"calls":[129],"do":[130],"not":[131],"guarantee":[132],"successful":[133],"recommendations.Models":[134],"struggle":[135],"semantic":[137],"parameter":[138],"grounding,":[139],"multi-step":[140],"evidence":[141],"integration,":[142],"grounded":[144],"final":[145],"recommendations,":[146],"especially":[147],"as":[148,160],"complexity":[150],"increases.Our":[151],"results":[152],"identify":[153],"intent":[159],"major":[162],"bottleneck":[163],"systems.Our":[167],"data":[168],"code":[170],"available":[172],"at":[173],"https://github.com/":[174],"ShawnChenn/RecToolBench.":[175]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-09-29T00:00:00"}