{"id":"https://openalex.org/W7214770873","doi":"https://doi.org/10.48550/arxiv.2609.31632","title":"EEGAgentBench: Benchmarking LLM Agents on Short- and Long-Horizon EEG Analysis","display_name":"EEGAgentBench: Benchmarking LLM Agents on Short- and Long-Horizon EEG Analysis","publication_year":2026,"publication_date":"2026-09-10","ids":{"openalex":"https://openalex.org/W7214770873","doi":"https://doi.org/10.48550/arxiv.2609.31632"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.31632","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.31632","pdf_url":"https://arxiv.org/pdf/2609.31632","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.31632","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135650247","display_name":"Huyu Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Huyu","raw_affiliation_strings":["Institute of Computing Technology , Chinese Academy of Sciences , Beijing , China","University of Chinese Academy of Sciences , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology , Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102900693","display_name":"Weining Weng","orcid":"https://orcid.org/0009-0008-5006-1262","observed_orcids":["https://orcid.org/0009-0008-5006-1262"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weng, Weining","raw_affiliation_strings":["Institute of Computing Technology , Chinese Academy of Sciences , Beijing , China","University of Chinese Academy of Sciences , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology , Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153410575","display_name":"Yuchen Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Yuchen","raw_affiliation_strings":["Institute of Computing Technology , Chinese Academy of Sciences , Beijing , China","University of Chinese Academy of Sciences , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology , Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153551981","display_name":"Yiqiang Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Yiqiang","raw_affiliation_strings":["Institute of Computing Technology , Chinese Academy of Sciences , Beijing , China","University of Chinese Academy of Sciences , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology , Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153409969","display_name":"Yang Gu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gu, Yang","raw_affiliation_strings":["Institute of Computing Technology , Chinese Academy of Sciences , Beijing , China","University of Chinese Academy of Sciences , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology , Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.0012000000569969416,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.0003000000142492354,"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/eeg-analysis","display_name":"EEG signal analysis","score":0.8479999899864197},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.8870000243186951},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.39399999380111694},{"id":"https://openalex.org/keywords/multi-step-reasoning","display_name":"multi-step reasoning","score":0.7170000076293945},{"id":"https://openalex.org/keywords/tool-use","display_name":"tool use","score":0.7229999899864197},{"id":"https://openalex.org/keywords/evidence-accumulation","display_name":"evidence accumulation","score":0.6340000033378601},{"id":"https://openalex.org/keywords/sleep-staging","display_name":"sleep stage classification","score":0.6380000114440918},{"id":"https://openalex.org/keywords/eeg-classification","display_name":"EEG classification","score":0.5789999961853027},{"id":"https://openalex.org/keywords/event-detection","display_name":"event detection","score":0.6129999756813049},{"id":"https://openalex.org/keywords/agent-evaluation","display_name":"agent evaluation","score":0.4059999883174896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7247999906539917},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7074000239372253},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7006000280380249},{"id":"https://openalex.org/C522805319","wikidata":"https://www.wikidata.org/wiki/Q179965","display_name":"Electroencephalography","level":2,"score":0.6947000026702881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5719000101089478},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5536999702453613},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5396999716758728},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5347999930381775},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.49970000982284546},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2890999913215637}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.31632","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.31632","pdf_url":"https://arxiv.org/pdf/2609.31632","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.2609.31632","doi":"https://doi.org/10.48550/arxiv.2609.31632","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.31632","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:2609.31632","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.31632","pdf_url":"https://arxiv.org/pdf/2609.31632","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214770873.pdf","grobid_xml":"https://content.openalex.org/works/W7214770873.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2144691514","https://openalex.org/W2909338255","https://openalex.org/W4320003957","https://openalex.org/W4378528024","https://openalex.org/W4399836817","https://openalex.org/W4402597889","https://openalex.org/W4416414700","https://openalex.org/W4417288933","https://openalex.org/W7101416451","https://openalex.org/W7160921870","https://openalex.org/W7165889050"],"related_works":["https://openalex.org/W7197033200","https://openalex.org/W7137929362","https://openalex.org/W7221702563","https://openalex.org/W7171651505","https://openalex.org/W7166057138","https://openalex.org/W4417116223","https://openalex.org/W7129702654","https://openalex.org/W7167932583","https://openalex.org/W4411552749","https://openalex.org/W4411394944"],"abstract_inverted_index":{"Electroencephalography":[0],"(EEG)":[1],"analysis":[2,151],"is":[3],"evolving":[4],"from":[5,97,108,119,179],"short-segment":[6],"classification":[7],"toward":[8],"long-horizon":[9,87,138,206],"interpretation":[10],"that":[11,153,185],"demands":[12],"iterative":[13],"evidence":[14,166,212],"accumulation,":[15],"multi-step":[16,170,215],"reasoning,":[17,63,135],"and":[18,56,65,86,125,141,168,194,214],"coordinated":[19],"use":[20],"of":[21,61,201],"specialized":[22],"signal-processing":[23],"tools.":[24],"Although":[25],"large":[26],"language":[27],"models":[28],"(LLMs)":[29],"have":[30],"recently":[31],"shown":[32],"promise":[33],"as":[34],"autonomous":[35],"agents":[36,83,204],"for":[37,79],"EEG":[38,41,88,94,150,207],"analysis,":[39,208],"existing":[40],"agentic":[42],"evaluations":[43],"remain":[44],"fragmented,":[45],"covering":[46],"limited":[47],"tasks":[48],"over":[49],"narrow":[50],"temporal":[51],"horizons":[52],"with":[53,115],"inconsistent":[54],"protocols,":[55],"providing":[57],"no":[58],"comprehensive":[59],"assessment":[60],"agents'":[62],"tool-use,":[64],"workflow":[66],"construction":[67],"capabilities.":[68],"To":[69],"address":[70],"this":[71],"gap,":[72],"we":[73,174],"propose":[74],"\\textbf{EEGAgentBench},":[75],"a":[76],"unified":[77,131],"benchmark":[78,145,175],"systematically":[80],"evaluating":[81],"LLM":[82,203],"on":[84],"short-":[85],"analysis.":[89],"EEGAgentBench":[90,186],"spans":[91],"six":[92],"representative":[93],"applications":[95],"ranging":[96,118],"knowledge":[98,134],"question":[99],"answering":[100],"to":[101,111,122],"sleep":[102],"staging.":[103],"It":[104],"encompasses":[105],"signal":[106,157],"durations":[107],"2":[109],"seconds":[110],"nearly":[112],"23":[113],"hours,":[114],"prediction":[116],"targets":[117],"class":[120],"labels":[121],"event":[123,139],"intervals":[124],"epoch-level":[126],"sequences.":[127],"This":[128],"design":[129],"supports":[130],"evaluation":[132],"across":[133],"short-horizon":[136],"interpretation,":[137],"detection,":[140],"sequential":[142],"understanding.":[143],"The":[144],"further":[146],"provides":[147],"10":[148],"deterministic":[149],"tools":[152,163],"expose":[154],"only":[155],"task-relevant":[156],"measurements.":[158],"Agents":[159],"must":[160],"therefore":[161],"select":[162],"autonomously,":[164],"accumulate":[165],"iteratively,":[167],"construct":[169],"workflows.":[171],"For":[172],"evaluation,":[173],"29":[176],"frontier":[177],"LLMs":[178],"15":[180],"model":[181,192],"families.":[182],"Results":[183],"demonstrate":[184],"effectively":[187],"distinguishes":[188],"agent":[189],"capabilities":[190],"beyond":[191],"scale":[193],"inference":[195],"cost,":[196],"while":[197],"revealing":[198],"substantial":[199],"limitations":[200],"current":[202],"in":[205,210],"particularly":[209],"sustained":[211],"accumulation":[213],"reasoning.":[216]},"counts_by_year":[],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2026-09-30T00:00:00"}