{"id":"https://openalex.org/W7160421540","doi":"https://doi.org/10.48550/arxiv.2605.03808","title":"Agentic-imodels: Evolving agentic interpretability tools via autoresearch","display_name":"Agentic-imodels: Evolving agentic interpretability tools via autoresearch","publication_year":2026,"publication_date":"2026-05-05","ids":{"openalex":"https://openalex.org/W7160421540","doi":"https://doi.org/10.48550/arxiv.2605.03808"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.03808","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.03808","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.03808","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135431534","display_name":"Chandan Singh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Singh, Chandan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135425940","display_name":"Yan Shuo Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Yan Shuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135522108","display_name":"Weijia Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Weijia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135537222","display_name":"Zelalem Gero","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gero, Zelalem","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135425579","display_name":"Weiwei Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Weiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107838508","display_name":"Michel Galley","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Galley, Michel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135521652","display_name":"Jianfeng Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Jianfeng","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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8912000060081482,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.8912000060081482,"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":0.010499999858438969,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0071000000461936,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/interpretability","display_name":"Interpretability","score":0.9660999774932861},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6284000277519226},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6177999973297119},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.604200005531311},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5924999713897705},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5580999851226807},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.367900013923645}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9660999774932861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6507999897003174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6484000086784363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6340000033378601},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6284000277519226},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6177999973297119},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.604200005531311},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5924999713897705},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5580999851226807},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.367900013923645},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C2780977526","wikidata":"https://www.wikidata.org/wiki/Q42417149","display_name":"Data exploration","level":3,"score":0.34610000252723694},{"id":"https://openalex.org/C2778565505","wikidata":"https://www.wikidata.org/wiki/Q2207566","display_name":"Spec#","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.03808","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.03808","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.03808","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.03808","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,"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"},"sustainable_development_goals":[{"score":0.5905203223228455,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Agentic":[0],"data":[1,79],"science":[2],"(ADS)":[3],"systems":[4,34],"are":[5,81],"rapidly":[6],"improving":[7],"their":[8],"capability":[9],"to":[10,39,64,145,175],"autonomously":[11],"analyze,":[12],"fit,":[13],"and":[14,87,141,148,167],"interpret":[15],"data,":[16],"potentially":[17],"moving":[18],"towards":[19],"a":[20,72,88,96,104],"future":[21],"where":[22],"agents":[23],"conduct":[24],"the":[25,116,122,134,170],"vast":[26],"majority":[27],"of":[28,74,98],"data-science":[29,61],"work.":[30],"However,":[31],"current":[32],"ADS":[33],"use":[35],"statistical":[36],"tools":[37,62],"designed":[38,63],"be":[40,65],"interpretable":[41,46,66],"by":[42,47,67,111,125,173],"humans,":[43],"rather":[44],"than":[45],"agents.":[48,68],"To":[49],"address":[50],"this,":[51],"we":[52],"introduce":[53],"Agentic-imodels,":[54],"an":[55,112],"agentic":[56],"autoresearch":[57],"loop":[58],"that":[59,80,101,133],"evolves":[60],"Specifically,":[69],"it":[70],"develops":[71],"library":[73],"scikit-learn-compatible":[75],"regressors":[76],"for":[77,83,162],"tabular":[78],"optimized":[82],"both":[84],"predictive":[85,139],"performance":[86,140,161],"novel":[89],"LLM-based":[90],"interpretability":[91,150],"metric.":[92],"The":[93],"metric":[94],"measures":[95],"suite":[97],"LLM-graded":[99],"tests":[100],"probe":[102],"whether":[103,115],"fitted":[105],"model's":[106,123],"string":[107,128],"representation":[108],"is":[109],"\"simulatable\"":[110],"LLM,":[113],"i.e.":[114],"LLM":[117],"can":[118],"answer":[119],"questions":[120],"about":[121],"behavior":[124],"reading":[126],"its":[127],"output":[129],"alone.":[130],"We":[131],"find":[132],"evolved":[135,154],"models":[136,155],"jointly":[137],"improve":[138,156],"agent-facing":[142],"interpretability,":[143],"generalizing":[144],"new":[146,149],"datasets":[147],"tests.":[151],"Furthermore,":[152],"these":[153],"downstream":[157],"end-to-end":[158],"ADS,":[159],"increasing":[160],"Copilot":[163],"CLI,":[164],"Claude":[165],"Code,":[166],"Codex":[168],"on":[169],"BLADE":[171],"benchmark":[172],"up":[174],"73%":[176]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-07T00:00:00"}