{"id":"https://openalex.org/W4416190659","doi":"https://doi.org/10.1145/3774904.3792551","title":"AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress","display_name":"AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W4416190659","doi":"https://doi.org/10.1145/3774904.3792551"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792551","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792551","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792551","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036875405","display_name":"Zhiheng Xi","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiheng Xi","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8299-8449","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030090567","display_name":"Chenyang Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Liao","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-7470-4193","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Guanyu Li","orcid":"https://orcid.org/0009-0001-0577-406X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanyu Li","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-0577-406X","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhihao Zhang","orcid":"https://orcid.org/0009-0008-1526-104X"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-1526-104X","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenxiang Chen","orcid":"https://orcid.org/0009-0006-3492-6663"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxiang Chen","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-3492-6663","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Binghai Wang","orcid":"https://orcid.org/0009-0005-9137-7886"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binghai Wang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-9137-7886","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Senjie Jin","orcid":"https://orcid.org/0009-0003-4720-6524"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Senjie Jin","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-4720-6524","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuhao Zhou","orcid":"https://orcid.org/0009-0008-8665-3999"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Zhou","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-8665-3999","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jian Guan","orcid":"https://orcid.org/0000-0002-3597-0176"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Guan","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3597-0176","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Wu","orcid":"https://orcid.org/0000-0001-6079-7697"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Wu","raw_affiliation_strings":["Ant Group, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6079-7697","affiliations":[{"raw_affiliation_string":"Ant Group, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tao Ji","orcid":"https://orcid.org/0000-0002-9957-6661"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Ji","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9957-6661","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tao Gui","orcid":"https://orcid.org/0000-0002-0059-0210"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Gui","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0059-0210","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0003-0947-4942"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0947-4942","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xuanjing Huang","orcid":"https://orcid.org/0000-0001-9197-9426"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanjing Huang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9197-9426","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4184","last_page":"4195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3149999976158142,"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/T10028","display_name":"Topic Modeling","score":0.3149999976158142,"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":0.12690000236034393,"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"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.1265999972820282,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7031999826431274},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6477000117301941},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.3382999897003174},{"id":"https://openalex.org/keywords/work-in-process","display_name":"Work in process","score":0.31610000133514404},{"id":"https://openalex.org/keywords/data-driven","display_name":"Data-driven","score":0.28949999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7770000100135803},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7031999826431274},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6477000117301941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5799999833106995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5327000021934509},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C174998907","wikidata":"https://www.wikidata.org/wiki/Q357662","display_name":"Work in process","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2766000032424927},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.271699994802475}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3774904.3792551","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792551","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.08325","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.08325","pdf_url":"https://arxiv.org/pdf/2511.08325","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.08325","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.08325","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792551","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792551","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"rapid":[1],"development,":[2],"large":[3],"language":[4],"models":[5,67],"(LLMs)":[6],"still":[7],"encounter":[8],"challenges":[9],"in":[10,91],"multi-turn":[11],"decision-making":[12,77],"tasks":[13,93,189],"(i.e.,":[14],"agent":[15,92,128],"tasks)":[16],"like":[17],"web":[18],"shopping":[19],"and":[20,73,112,140,152,200,221],"browser":[21],"navigation,":[22],"which":[23,177],"require":[24],"making":[25],"a":[26,59,97,124,165],"sequence":[27],"of":[28,232],"intelligent":[29],"decisions":[30,139],"based":[31,87,105],"on":[32,42,88,106,119],"environmental":[33],"feedback.":[34],"Previous":[35],"work":[36],"for":[37,127,160],"LLM":[38,80,233],"agents":[39],"typically":[40],"relies":[41],"elaborate":[43],"prompt":[44],"engineering":[45],"or":[46],"fine-tuning":[47],"with":[48,172],"expert":[49],"trajectories":[50],"to":[51,69,109,132,143,215,228],"improve":[52],"performance.":[53],"In":[54],"this":[55,120],"work,":[56],"we":[57,62,122,163,211],"take":[58],"different":[60,187],"perspective:":[61],"explore":[63],"constructing":[64],"process":[65],"reward":[66],"(PRMs)":[68],"evaluate":[70],"each":[71,83],"decision":[72],"guide":[74],"the":[75,110,113,135,144,229],"agent's":[76],"process.":[78],"Unlike":[79],"reasoning,":[81],"where":[82],"step":[84],"is":[85,193],"scored":[86],"correctness,":[89],"actions":[90],"do":[94],"not":[95],"have":[96,116],"clear-cut":[98],"correctness.":[99],"Instead,":[100],"they":[101,115],"should":[102],"be":[103],"evaluated":[104],"their":[107,141],"proximity":[108],"goal":[111],"progress":[114,150],"made.":[117],"Building":[118],"insight,":[121],"propose":[123],"re-defined":[125],"PRM":[126],"tasks,":[129],"named":[130],"AgentPRM,":[131,162],"capture":[133],"both":[134],"interdependence":[136],"between":[137],"sequential":[138],"contribution":[142],"final":[145],"goal.":[146],"This":[147],"enables":[148],"better":[149],"tracking":[151],"exploration-exploitation":[153],"balance.":[154],"To":[155],"scalably":[156],"obtain":[157],"labeled":[158],"data":[159],"training":[161],"employ":[164],"Temporal":[166],"Difference-based":[167],"(TD-based)":[168],"estimation":[169],"method":[170,219],"combined":[171],"Generalized":[173],"Advantage":[174],"Estimation":[175],"(GAE),":[176],"proves":[178],"more":[179,196,223],"sample-efficient":[180],"than":[181,198],"prior":[182],"methods.":[183],"Extensive":[184],"experiments":[185],"across":[186],"agentic":[188],"show":[190,216],"that":[191],"AgentPRM":[192,227],"over":[194],"8\u00d7":[195],"compute-efficient":[197],"baselines,":[199],"it":[201],"demonstrates":[202],"robust":[203],"improvement":[204],"when":[205],"scaling":[206],"up":[207],"test-time":[208],"compute.":[209],"Moreover,":[210],"perform":[212],"detailed":[213],"analyses":[214],"how":[217],"our":[218],"works":[220],"offer":[222],"insights,":[224],"e.g.,":[225],"applying":[226],"reinforcement":[230],"learning":[231],"agents.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-13T00:00:00"}