{"id":"https://openalex.org/W4416366334","doi":"https://doi.org/10.18653/2026.emnlp-main.1304","title":"GUI-PRA: Process Reward Agents for GUI Tasks","display_name":"GUI-PRA: Process Reward Agents for GUI Tasks","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416366334","doi":"https://doi.org/10.18653/2026.emnlp-main.1304"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.1304","doi":"https://doi.org/10.18653/2026.emnlp-main.1304","is_oa":false,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1304","pdf_url":null,"source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.23263","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tao Xiong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Xiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xueyu Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xueyu Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yurun Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yurun Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420950","display_name":"Yuhang Liu","orcid":"https://orcid.org/0000-0001-5687-184X","observed_orcids":["https://orcid.org/0000-0001-5687-184X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Changqiao Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changqiao Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119805131","display_name":"Pengzhi Gao","orcid":"https://orcid.org/0009-0009-9392-6657","observed_orcids":["https://orcid.org/0009-0009-9392-6657"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengzhi Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100745747","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-9104-6316","observed_orcids":["https://orcid.org/0000-0002-9104-6316"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103233031","display_name":"Jian Luan","orcid":"https://orcid.org/0009-0005-2377-4126","observed_orcids":["https://orcid.org/0009-0005-2377-4126"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Luan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100757088","display_name":"Shengyu Zhang","orcid":"https://orcid.org/0000-0002-5090-9867","observed_orcids":["https://orcid.org/0000-0002-5090-9867","https://orcid.org/0009-0000-9356-2501"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengyu Zhang","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00896287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"29695","last_page":"29716"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.7050999999046326,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.7050999999046326,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T13287","display_name":"Robotic Process Automation Applications","score":0.0406000018119812,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.02500000037252903,"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/gui-automation","display_name":"GUI automation","score":0.6859999895095825},{"id":"https://openalex.org/keywords/process-reward-models","display_name":"process reward models","score":0.8410000205039978},{"id":"https://openalex.org/keywords/long-horizon-interaction","display_name":"long-horizon interaction","score":0.703000009059906},{"id":"https://openalex.org/keywords/visual-ambiguity","display_name":"visual ambiguity","score":0.6349999904632568},{"id":"https://openalex.org/keywords/error-accumulation","display_name":"error accumulation","score":0.6039999723434448},{"id":"https://openalex.org/keywords/qwen-vl","display_name":"Qwen-VL","score":0.6620000004768372}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8302000164985657},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6977999806404114},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6625000238418579},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5957000255584717},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.5605000257492065},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.5529999732971191},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4302999973297119},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4189000129699707},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3508000075817108},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.1304","doi":"https://doi.org/10.18653/2026.emnlp-main.1304","is_oa":false,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.1304","pdf_url":null,"source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.23263","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.23263","pdf_url":"https://arxiv.org/pdf/2509.23263","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.23263","doi":"https://doi.org/10.48550/arxiv.2509.23263","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.23263","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.23263","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.23263","pdf_url":"https://arxiv.org/pdf/2509.23263","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":null,"license_id":null,"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/W4415332682","https://openalex.org/W7223020125","https://openalex.org/W7165760727","https://openalex.org/W4415255629","https://openalex.org/W7171623769","https://openalex.org/W7138260847","https://openalex.org/W4416375922","https://openalex.org/W7125201106","https://openalex.org/W7131667860","https://openalex.org/W7138102159"],"abstract_inverted_index":{"Long-horizon":[0],"GUI":[1,32,91],"automation":[2],"remains":[3],"challenging":[4],"due":[5],"to":[6,31,121],"error":[7,23],"accumulation":[8],"over":[9,141],"extended":[10],"interaction":[11],"sequences.":[12],"Process":[13,86],"Reward":[14,87],"Models":[15],"(PRMs)":[16],"provide":[17],"dense":[18],"step-level":[19],"supervision":[20],"for":[21],"mitigating":[22],"accumulation,":[24],"yet":[25],"standard":[26,142],"PRMs":[27,59,143],"are":[28],"poorly":[29],"suited":[30],"verification.":[33],"Standard":[34,58],"PRM":[35],"judgments":[36],"often":[37],"rely":[38],"on":[39,144,154],"superficial":[40],"visual":[41,64,124],"alignment":[42],"rather":[43],"than":[44],"functional":[45],"correctness,":[46],"reflecting":[47],"an":[48],"evaluative":[49],"knowledge":[50],"gap":[51],"caused":[52],"by":[53],"missing":[54],"domain-specific":[55],"adjudication":[56],"logic.":[57],"also":[60],"perform":[61],"passive,":[62],"single-pass":[63],"assessment,":[65],"which":[66,105,117],"creates":[67],"Visual":[68],"Ambiguity":[69],"when":[70],"reliable":[71],"judgment":[72],"requires":[73],"actively":[74],"locating,":[75],"parsing,":[76],"or":[77],"inspecting":[78],"task-relevant":[79],"UI":[80],"evidence.":[81,129],"We":[82],"introduce":[83],"GUI-PRA,":[84],"a":[85],"Agent":[88],"that":[89],"transforms":[90],"process":[92],"evaluation":[93],"from":[94],"passive":[95],"scoring":[96],"into":[97,110],"active":[98],"investigation.":[99],"GUI-PRA":[100,134,161],"couples":[101],"Experience-Injected":[102],"Criterion":[103],"Synthesis,":[104],"distills":[106],"generalized":[107],"verification":[108],"principles":[109],"state-specific":[111],"criteria,":[112],"with":[113,148],"Criterion-Guided":[114],"Autoregressive":[115],"Perception,":[116],"uses":[118],"these":[119],"criteria":[120],"navigate":[122],"multi-granularity":[123],"tools":[125],"and":[126,132,139],"gather":[127],"grounded":[128],"On":[130,156],"AndroidWorld":[131],"Mobile-MiniWoB++,":[133],"achieves":[135],"improvements":[136],"of":[137],"5.0%":[138],"6.5%":[140],"the":[145,157],"Qwen-VL":[146],"series,":[147],"Qwen3-VL":[149],"attaining":[150],"54.74%":[151],"success":[152],"rate":[153],"AndroidWorld.":[155],"offline":[158],"OS-Critic":[159],"Bench,":[160],"demonstrates":[162],"strong":[163],"competitiveness":[164],"against":[165],"fully":[166],"trained":[167],"critic":[168],"models.":[169]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2025-10-10T00:00:00"}