{"id":"https://openalex.org/W4394776438","doi":"https://doi.org/10.48550/arxiv.2404.06474","title":"Autonomous Evaluation and Refinement of Digital Agents","display_name":"Autonomous Evaluation and Refinement of Digital Agents","publication_year":2024,"publication_date":"2024-04-09","ids":{"openalex":"https://openalex.org/W4394776438","doi":"https://doi.org/10.48550/arxiv.2404.06474"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2404.06474","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.06474","pdf_url":"https://arxiv.org/pdf/2404.06474","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/2404.06474","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103512739","display_name":"Jiayi Pan","orcid":"https://orcid.org/0009-0007-0468-4592","observed_orcids":["https://orcid.org/0009-0007-0468-4592"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Jiayi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444182","display_name":"Yichi Zhang","orcid":"https://orcid.org/0000-0002-0573-8050","observed_orcids":["https://orcid.org/0000-0002-0573-8050"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yichi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013447238","display_name":"Nicholas Tomlin","orcid":"https://orcid.org/0000-0001-6502-989X","observed_orcids":["https://orcid.org/0000-0001-6502-989X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomlin, Nicholas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhou, Yifei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yifei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743","observed_orcids":["https://orcid.org/0000-0001-6764-2743"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Levine, Sergey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5009625151","display_name":"Alane Suhr","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suhr, Alane","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":3,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.2517000138759613,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.2517000138759613,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.1923999935388565,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.16850000619888306,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/digital-agents","display_name":"digital agents","score":0.6679999828338623},{"id":"https://openalex.org/keywords/inference-cost","display_name":"inference cost","score":0.7870000004768372},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.7559999823570251}],"concepts":[{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.8420823812484741},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8374534845352173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8256122469902039},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7400321960449219},{"id":"https://openalex.org/C2779478453","wikidata":"https://www.wikidata.org/wiki/Q6889748","display_name":"Modularity (biology)","level":2,"score":0.700820803642273},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6733332872390747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4814283549785614},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45380690693855286},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42250627279281616},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.21262437105178833},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08415117859840393},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2404.06474","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.06474","pdf_url":"https://arxiv.org/pdf/2404.06474","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.2404.06474","doi":"https://doi.org/10.48550/arxiv.2404.06474","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2404.06474","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:2404.06474","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.06474","pdf_url":"https://arxiv.org/pdf/2404.06474","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":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415154343","https://openalex.org/W7202371368","https://openalex.org/W4417233452","https://openalex.org/W4403820931","https://openalex.org/W7166851887","https://openalex.org/W7172296557","https://openalex.org/W7220675183","https://openalex.org/W4415334925","https://openalex.org/W7147545502","https://openalex.org/W7166849922"],"abstract_inverted_index":{"We":[0,19,36],"show":[1],"that":[2,25],"domain-general":[3],"automatic":[4],"evaluators":[5,64],"can":[6],"significantly":[7],"improve":[8,66,82],"the":[9,38,67,88],"performance":[10,39,68,84],"of":[11,32,40,69],"agents":[12,71],"for":[13,47],"web":[14],"navigation":[15],"and":[16,34,53,74,92],"device":[17,99],"control.":[18],"experiment":[20],"with":[21,56],"multiple":[22],"evaluation":[23,58],"models":[24,42],"trade":[26],"off":[27],"between":[28,51],"inference":[29],"cost,":[30],"modularity":[31],"design,":[33],"accuracy.":[35],"validate":[37],"these":[41,63],"in":[43,98],"several":[44],"popular":[45,89],"benchmarks":[46],"digital":[48],"agents,":[49],"finding":[50],"74.4":[52],"92.9%":[54],"agreement":[55],"oracle":[57],"metrics.":[59],"Finally,":[60],"we":[61,81],"use":[62],"to":[65],"existing":[70],"via":[72],"fine-tuning":[73],"inference-time":[75],"guidance.":[76],"Without":[77],"any":[78],"additional":[79],"supervision,":[80],"state-of-the-art":[83],"by":[85],"29%":[86],"on":[87],"benchmark":[90],"WebArena,":[91],"achieve":[93],"around":[94],"75%":[95],"relative":[96],"improvement":[97],"control":[100],"settings.":[101]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-09-27T08:07:27.782135","created_date":"2024-04-13T00:00:00"}