{"id":"https://openalex.org/W7164174115","doi":"https://doi.org/10.48550/arxiv.2606.11182","title":"EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents","display_name":"EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents","publication_year":2026,"publication_date":"2026-06-09","ids":{"openalex":"https://openalex.org/W7164174115","doi":"https://doi.org/10.48550/arxiv.2606.11182"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.11182","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11182","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.11182","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132696415","display_name":"Weixian Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Weixian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138375827","display_name":"Shilong Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Shilong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138333728","display_name":"Mengdi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Mengdi","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":false,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.2883000075817108,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.2883000075817108,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.08500000089406967,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.08049999922513962,"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/router","display_name":"Router","score":0.6413000226020813},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.6223000288009644},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5996999740600586},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5738000273704529},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.4097000062465668},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.36570000648498535}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8003000020980835},{"id":"https://openalex.org/C2775896111","wikidata":"https://www.wikidata.org/wiki/Q642560","display_name":"Router","level":2,"score":0.6413000226020813},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6223000288009644},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5996999740600586},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5738000273704529},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.499099999666214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4934000074863434},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.36570000648498535},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.29580000042915344},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2937000095844269},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.11182","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11182","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.11182","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11182","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"EEVEE,":[5],"the":[6,104],"first":[7],"multi-dataset":[8],"test-time":[9,17],"prompt":[10,18,74,90],"learning":[11,19,91,115],"framework":[12,105],"for":[13,29],"LLM":[14],"agents,":[15],"enabling":[16],"under":[20,108],"real-world":[21,33],"task":[22,48,67],"streams.":[23],"Existing":[24],"methods":[25,136],"are":[26],"largely":[27],"designed":[28],"single-dataset":[30],"settings,":[31],"while":[32,112],"applications":[34],"require":[35],"models":[36],"to":[37,72,93,142],"handle":[38],"heterogeneous":[39,109],"input":[40],"streams":[41,111],"drawn":[42],"from":[43],"multiple":[44,100],"datasets,":[45],"domains,":[46],"and":[47,69,89,117,127,132,138,144],"distributions,":[49],"limiting":[50],"their":[51,95],"practical":[52],"applicability.":[53],"To":[54],"mitigate":[55],"cross-dataset":[56],"interference,":[57],"EEVEE":[58,120],"introduces":[59],"a":[60,81],"router":[61,88],"that":[62,103],"partitions":[63],"incoming":[64],"inputs":[65],"into":[66],"clusters":[68],"assigns":[70],"them":[71],"suitable":[73],"configurations.":[75],"This":[76],"design":[77],"is":[78],"optimized":[79],"via":[80],"router-prompt":[82],"co-evolution":[83],"strategy,":[84],"which":[85],"employs":[86],"interleaved":[87],"phases":[92],"address":[94],"mutual":[96],"dependency.":[97],"Experiments":[98],"across":[99],"datasets":[101],"demonstrate":[102],"improves":[106,121],"robustness":[107],"data":[110],"maintaining":[113],"single-benchmark":[114],"capability":[116],"efficiency.":[118],"Specifically,":[119],"average":[122],"multi-benchmark":[123],"scores":[124],"by":[125,140],"10.38":[126],"24.32":[128],"points":[129],"over":[130],"Qwen3-4B-Instruct":[131],"DeepSeek-V3.2,":[133],"surpassing":[134],"SOTA":[135],"GEPA":[137],"ACE":[139],"up":[141],"37.2%":[143],"48.2%.":[145]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-11T00:00:00"}