{"id":"https://openalex.org/W7140121197","doi":"https://doi.org/10.18653/v1/2026.eacl-long.175","title":"FormGym: Doing Paperwork with Agents","display_name":"FormGym: Doing Paperwork with Agents","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140121197","doi":"https://doi.org/10.18653/v1/2026.eacl-long.175"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.175","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.175","pdf_url":"https://aclanthology.org/2026.eacl-long.175.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.eacl-long.175.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120048095","display_name":"Matthew Toles","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthew Toles","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130399095","display_name":"Isaac Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Isaac Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120048096","display_name":"Rattandeep Singh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rattandeep Singh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130333000","display_name":"Zhou Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34428656,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3771","last_page":"3785"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10789","display_name":"Interactive and Immersive Displays","score":0.4260999858379364,"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"}},"topics":[{"id":"https://openalex.org/T10789","display_name":"Interactive and Immersive Displays","score":0.4260999858379364,"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"}},{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.062199998646974564,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10470","display_name":"Usability and User Interface Design","score":0.057500001043081284,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7828999757766724},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.628000020980835},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5954999923706055},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5853999853134155},{"id":"https://openalex.org/keywords/repurposing","display_name":"Repurposing","score":0.5773000121116638},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5551999807357788},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.43320000171661377}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7828999757766724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7210999727249146},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.628000020980835},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5954999923706055},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5853999853134155},{"id":"https://openalex.org/C519536355","wikidata":"https://www.wikidata.org/wiki/Q21021151","display_name":"Repurposing","level":2,"score":0.5773000121116638},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5551999807357788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4634999930858612},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4514000117778778},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C2776904630","wikidata":"https://www.wikidata.org/wiki/Q356336","display_name":"Adept","level":3,"score":0.4327999949455261},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3614000082015991},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2865000069141388},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26829999685287476},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.175","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.175","pdf_url":"https://aclanthology.org/2026.eacl-long.175.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.175","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.175","pdf_url":"https://aclanthology.org/2026.eacl-long.175.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.42767032980918884,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140121197.pdf","grobid_xml":"https://content.openalex.org/works/W7140121197.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"End-to-end":[0],"form":[1,11,30,40,57,62],"filling":[2,58],"refers":[3],"to":[4,78,103,129,148],"automatically":[5],"populating":[6],"fields":[7],"in":[8,98,135,150],"a":[9,51,121],"document-style":[10,47],"with":[12,142],"the":[13,55],"appropriate":[14],"information":[15],"derived":[16],"from":[17,112],"external":[18],"data.Although":[19],"prevalent":[20],"and":[21,38,64,73,83,115,131],"useful,":[22],"no":[23],"formal":[24],"benchmark":[25,52],"exists":[26],"for":[27],"evaluating":[28],"systems'":[29],"completion":[31,45,63],"accuracy.Existing":[32],"datasets":[33,72],"focus":[34],"on":[35,96],"parsing,":[36],"extraction":[37],"web":[39],"interaction,":[41],"rather":[42],"than":[43],"end-to-end":[44],"of":[46,54],"forms.We":[48],"propose":[49],"Form-Gym,":[50],"formulation":[53],"end-toend":[56],"task":[59],"that":[60,125,139],"evaluates":[61],"accuracy.We":[65],"construct":[66],"FormGym":[67,97],"by":[68],"repurposing":[69],"three":[70],"existing":[71],"add":[74],"one":[75],"new":[76],"dataset":[77],"achieve":[79,144],"more":[80],"challenging,":[81],"diverse,":[82],"realistic":[84],"test":[85],"cases.Our":[86],"studies":[87],"show":[88],"baseline":[89],"vision":[90],"language":[91],"agents":[92,107],"(VLAs)":[93],"perform":[94,108],"poorly":[95],"every":[99],"scenario,":[100],"primarily":[101],"due":[102],"poor":[104],"field":[105,122],"localization.GUI":[106],"better":[109,145],"but":[110],"suffer":[111],"high":[113],"latency":[114],"costs.Therefore":[116],"we":[117],"also":[118],"introduce":[119],"FieldFinder,":[120],"localization":[123],"tool":[124],"enables":[126],"zero-shot":[127],"VLAs":[128,140],"find":[130,138],"accurately":[132],"place":[133],"text":[134],"input":[136],"fields.We":[137],"augmented":[141],"FieldFinder":[143],"performance":[146],"compared":[147],"baselines":[149],"all":[151],"models.":[152]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}