{"id":"https://openalex.org/W4415539798","doi":"https://doi.org/10.1145/3746027.3758285","title":"FormFactory: An Interactive Benchmarking Suite for Multimodal Form-Filling Agents","display_name":"FormFactory: An Interactive Benchmarking Suite for Multimodal Form-Filling Agents","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539798","doi":"https://doi.org/10.1145/3746027.3758285"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758285","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758285","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3758285","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101922939","display_name":"Bobo Li","orcid":"https://orcid.org/0000-0002-0513-5540"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bobo Li","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0513-5540","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006380484","display_name":"Yuheng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuheng Wang","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0007-5995-0077","affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Fei","orcid":"https://orcid.org/0000-0003-3026-6347"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hao Fei","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-3026-6347","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015420479","display_name":"Juncheng Li","orcid":"https://orcid.org/0000-0003-2258-1291"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juncheng Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2258-1291","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101397422","display_name":"Wei Ji","orcid":"https://orcid.org/0000-0002-8106-9768"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Ji","raw_affiliation_strings":["Nanjing University, Suzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8106-9768","affiliations":[{"raw_affiliation_string":"Nanjing University, Suzhou, China","institution_ids":["https://openalex.org/I3923682","https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019988958","display_name":"Mong Li Lee","orcid":"https://orcid.org/0000-0002-9636-388X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mong-Li Lee","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-9636-388X","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051209739","display_name":"Wynne Hsu","orcid":"https://orcid.org/0000-0002-4142-8893"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wynne Hsu","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4142-8893","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.4519,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.97487015,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"13273","last_page":"13280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11006","display_name":"BIM and Construction Integration","score":0.8543000221252441,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11006","display_name":"BIM and Construction Integration","score":0.8543000221252441,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T12290","display_name":"Human Motion and Animation","score":0.8475000262260437,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10672","display_name":"Design Education and Practice","score":0.8123000264167786,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.8686000108718872},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8465999960899353},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6784999966621399},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.675000011920929},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5709999799728394},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5389000177383423},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5138999819755554}],"concepts":[{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.8686000108718872},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8465999960899353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7811999917030334},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6784999966621399},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.675000011920929},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5709999799728394},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5396000146865845},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5389000177383423},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5138999819755554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44510000944137573},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.41429999470710754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.335099995136261},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.299699991941452},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3758285","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758285","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3758285","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3758285","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Online":[0],"form":[1,62,118],"filling":[2],"is":[3],"a":[4,95,122],"common":[5],"yet":[6],"labor-intensive":[7],"task":[8,87],"involving":[9],"extensive":[10],"keyboard":[11],"and":[12,31,68,88,101,115,128,155],"mouse":[13],"interactions.":[14,119],"Despite":[15],"the":[16,58,69,85,137,141],"long-standing":[17],"vision":[18],"of":[19,61,71,125,140],"automating":[20],"this":[21,80],"process":[22],"with":[23,57,75],"''one":[24],"click,''":[25],"existing":[26],"tools":[27],"remain":[28],"largely":[29],"rule-based":[30],"lack":[32],"generalizable,":[33],"generative":[34],"capabilities.":[35],"Recent":[36],"advances":[37],"in":[38,51,149],"Multimodal":[39],"Large":[40],"Language":[41],"Models":[42],"(MLLMs)":[43],"have":[44],"enabled":[45],"promising":[46],"agents":[47],"for":[48],"GUI-related":[49],"tasks":[50],"general-purpose":[52],"scenarios.":[53],"However,":[54],"they":[55],"struggle":[56],"unique":[59],"challenges":[60],"filling,":[63],"such":[64],"as":[65],"flexible":[66],"layouts":[67],"difficulty":[70,139],"aligning":[72],"textual":[73],"instructions":[74],"on-screen":[76],"fields.":[77],"To":[78],"bridge":[79],"gap,":[81],"we":[82],"formally":[83],"define":[84],"form-filling":[86],"propose":[89],"FormFactory-an":[90],"interactive":[91],"benchmarking":[92],"suite":[93],"comprising":[94],"web-based":[96],"interface,":[97],"backend":[98],"evaluation":[99,124],"module,":[100],"carefully":[102],"constructed":[103],"dataset.":[104],"Our":[105],"benchmark":[106],"covers":[107],"diverse":[108],"real-world":[109],"scenarios,":[110],"incorporates":[111],"various":[112],"field":[113],"formats,":[114],"simulates":[116],"high-fidelity":[117],"We":[120],"conduct":[121],"comprehensive":[123],"state-of-the-art":[126],"MLLMs":[127],"observe":[129],"that":[130],"no":[131],"model":[132],"surpasses":[133],"5%":[134],"accuracy,":[135],"underscoring":[136],"inherent":[138],"task.":[142],"These":[143],"findings":[144],"also":[145],"reveal":[146],"significant":[147],"limitations":[148],"current":[150],"models'":[151],"visual":[152],"layout":[153],"reasoning":[154],"field-value":[156],"alignment":[157],"abilities.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}
