{"id":"https://openalex.org/W7128005437","doi":"https://doi.org/10.48550/arxiv.2602.04482","title":"ProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World Data","display_name":"ProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World Data","publication_year":2026,"publication_date":"2026-02-04","ids":{"openalex":"https://openalex.org/W7128005437","doi":"https://doi.org/10.48550/arxiv.2602.04482"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.04482","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.04482","pdf_url":"https://arxiv.org/pdf/2602.04482","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.04482","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125157953","display_name":"Yuanbo Tang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Yuanbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125223268","display_name":"Huaze Tang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Huaze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033590193","display_name":"Tingyu Cao","orcid":"https://orcid.org/0000-0001-5846-3217","observed_orcids":["https://orcid.org/0000-0001-5846-3217"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Tingyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125247561","display_name":"Lam Nguyen","orcid":"https://orcid.org/0009-0003-0104-6166","observed_orcids":["https://orcid.org/0009-0003-0104-6166"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Lam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125222233","display_name":"Anping Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Anping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125149692","display_name":"Xinwen Cao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Xinwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125182683","display_name":"Chunkang Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Chunkang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068575030","display_name":"Wenbo Ding","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Wenbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125250099","display_name":"Yang Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, 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":null,"has_fulltext":true,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.2939000129699707,"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":0.2939000129699707,"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/T12031","display_name":"Speech and dialogue systems","score":0.16529999673366547,"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/T10470","display_name":"Usability and User Interface Design","score":0.05860000103712082,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/proactive-agents","display_name":"proactive agents","score":0.7549999952316284},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.847000002861023},{"id":"https://openalex.org/keywords/proactive-assistance","display_name":"proactive assistance","score":0.753000020980835},{"id":"https://openalex.org/keywords/user-intention-prediction","display_name":"user intention prediction","score":0.5989999771118164},{"id":"https://openalex.org/keywords/long-term-memory","display_name":"long-term memory","score":0.8399999737739563},{"id":"https://openalex.org/keywords/human-ai-interaction","display_name":"human-AI interaction","score":0.7739999890327454},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.42399999499320984},{"id":"https://openalex.org/keywords/video-language-models","display_name":"video-language models","score":0.4429999887943268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473999857902527},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.659500002861023},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6158999800682068},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5864999890327454},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5410000085830688},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47119998931884766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.424699991941452},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4075999855995178},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3935000002384186},{"id":"https://openalex.org/C142944206","wikidata":"https://www.wikidata.org/wiki/Q1786137","display_name":"Proactivity","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C71611378","wikidata":"https://www.wikidata.org/wiki/Q5165191","display_name":"Contextual design","level":3,"score":0.3215999901294708},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2985000014305115},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2980000078678131},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2906000018119812},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C61641136","wikidata":"https://www.wikidata.org/wiki/Q1107019","display_name":"Cognitive load","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C78639753","wikidata":"https://www.wikidata.org/wiki/Q3318160","display_name":"Behavioral modeling","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2513999938964844},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.04482","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.04482","pdf_url":"https://arxiv.org/pdf/2602.04482","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2602.04482","doi":"https://doi.org/10.48550/arxiv.2602.04482","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.04482","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":"pmh:oai:arXiv.org:2602.04482","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.04482","pdf_url":"https://arxiv.org/pdf/2602.04482","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128005437.pdf","grobid_xml":"https://content.openalex.org/works/W7128005437.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4403578058","https://openalex.org/W4415024665","https://openalex.org/W7161241358","https://openalex.org/W7169842549","https://openalex.org/W7214986222","https://openalex.org/W7110820691","https://openalex.org/W4416046351","https://openalex.org/W7153189630","https://openalex.org/W7093372144","https://openalex.org/W7154695734"],"abstract_inverted_index":{"Proactive":[0],"agents":[1,78],"that":[2,37,90,129,138],"anticipate":[3],"user":[4,113],"intentions":[5],"without":[6],"explicit":[7],"prompts":[8],"represent":[9],"a":[10,73,86,102],"significant":[11],"evolution":[12],"in":[13,79,122],"human-AI":[14],"interaction,":[15],"promising":[16],"to":[17,39],"reduce":[18],"cognitive":[19],"load":[20],"and":[21,45,97,125,132,141,160],"streamline":[22],"workflows.":[23],"However,":[24],"existing":[25],"datasets":[26],"suffer":[27],"from":[28,108],"two":[29],"critical":[30],"deficiencies:":[31],"(1)":[32,85],"reliance":[33],"on":[34,48],"LLM-synthesized":[35],"data":[36,151],"fails":[38],"capture":[40],"authentic":[41],"human":[42],"decision-making":[43],"patterns,":[44],"(2)":[46,101],"focus":[47],"isolated":[49],"tasks":[50],"rather":[51],"than":[52],"continuous":[53],"workflows,":[54],"missing":[55],"the":[56],"pre-assistance":[57],"behavioral":[58],"context":[59,143],"essential":[60],"for":[61,76],"learning":[62],"proactive":[63,77,92],"intervention":[64],"signals.":[65],"To":[66],"address":[67],"these":[68],"gaps,":[69],"we":[70,136],"introduce":[71],"ProAgentBench,":[72],"rigorous":[74],"benchmark":[75],"working":[80],"scenarios.":[81],"Our":[82],"contributions":[83],"include:":[84],"hierarchical":[87],"task":[88],"framework":[89],"decomposes":[91],"assistance":[93],"into":[94],"timing":[95],"prediction":[96,146],"assist":[98],"content":[99],"generation;":[100],"privacy-compliant":[103],"dataset":[104,159],"with":[105],"28,000+":[106],"events":[107],"500+":[109],"hours":[110],"of":[111],"real":[112],"sessions,":[114],"preserving":[115],"bursty":[116],"interaction":[117],"patterns":[118],"(burstiness":[119],"B=0.787)":[120],"absent":[121],"synthetic":[123,154],"data;":[124],"(3)":[126],"extensive":[127],"experiments":[128],"evaluates":[130],"LLM-":[131],"VLM-based":[133],"baselines.":[134],"Numerically,":[135],"showed":[137],"long-term":[139],"memory":[140],"historical":[142],"significantly":[144],"enhance":[145],"accuracy,":[147],"while":[148],"real-world":[149],"training":[150],"substantially":[152],"outperforms":[153],"alternatives.":[155],"We":[156],"release":[157],"our":[158],"code":[161],"at":[162],"https://anonymous.4open.science/r/ProAgentBench-6BC0.":[163]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-07T00:00:00"}