{"id":"https://openalex.org/W7166883808","doi":"https://doi.org/10.18653/v1/2026.findings-acl.458","title":"PhysPRM: A Generative Process Reward Model with Fine-grained Diagnosis for Physics Problem Solving","display_name":"PhysPRM: A Generative Process Reward Model with Fine-grained Diagnosis for Physics Problem Solving","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166883808","doi":"https://doi.org/10.18653/v1/2026.findings-acl.458"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.458","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.458","pdf_url":"https://aclanthology.org/2026.findings-acl.458.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.458.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108943954","display_name":"Yuxuan Dong","orcid":"https://orcid.org/0009-0004-9706-7275"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139744543","display_name":"Xinyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139744692","display_name":"Lingling Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingling Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139721563","display_name":"Han Lai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han Lai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139770924","display_name":"Pengyu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengyu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070094915","display_name":"Bifan Wei","orcid":"https://orcid.org/0000-0002-9732-3011"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bifan Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139776770","display_name":"Yaqiang Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaqiang Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139734155","display_name":"Jun Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Liu","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":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87250286,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9410","last_page":"9427"},"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":0.12039999663829803,"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":0.12039999663829803,"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/T10467","display_name":"Psychometric Methodologies and Testing","score":0.037300001829862595,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12805","display_name":"Cognitive Science and Mapping","score":0.03420000150799751,"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/process","display_name":"Process (computing)","score":0.5942000150680542},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3828999996185303},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3481999933719635},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.2694000005722046}],"concepts":[{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5942000150680542},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5026000142097473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47780001163482666},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3828999996185303},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.30160000920295715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28630000352859497},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2264000028371811},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.22010000050067902}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.458","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.458","pdf_url":"https://aclanthology.org/2026.findings-acl.458.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.458","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.458","pdf_url":"https://aclanthology.org/2026.findings-acl.458.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1661763918","display_name":null,"funder_award_id":"62293554","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2496375212","display_name":null,"funder_award_id":"62293550","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2965804137","display_name":null,"funder_award_id":"62477037","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4303215675","display_name":null,"funder_award_id":"62192781","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4712315907","display_name":null,"funder_award_id":"62437002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4896784468","display_name":null,"funder_award_id":"62137002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6311837223","display_name":null,"funder_award_id":"62293553","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G636632556","display_name":null,"funder_award_id":"62477036","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G723731210","display_name":null,"funder_award_id":"JYB2025XDXM116","funder_id":"https://openalex.org/F4320321106","funder_display_name":"Ministry of Education of the People's Republic of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321106","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166883808.pdf","grobid_xml":"https://content.openalex.org/works/W7166883808.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,64,139],"remarkable":[2],"progress":[3],"of":[4,143],"Large":[5],"Language":[6],"Models":[7,37],"(LLMs)":[8],"in":[9,24,159],"abstract":[10],"reasoning":[11,48,54,141],"tasks,":[12],"they":[13],"continue":[14],"to":[15,22,45,52,68,88,109,154],"struggle":[16],"with":[17,131],"physics":[18,140],"problem":[19],"solving":[20],"due":[21],"difficulties":[23],"decoding":[25],"implicit":[26],"constraints":[27],"and":[28,96,116,156,161],"maintaining":[29],"physical":[30,71],"consistency.To":[31],"address":[32],"these":[33],"challenges,":[34],"Process":[35],"Reward":[36],"(PRMs)":[38],"have":[39],"emerged":[40],"as":[41,84],"a":[42,78,85,112,118,123],"promising":[43],"approach":[44],"verify":[46],"intermediate":[47],"steps.Existing":[49],"PRMs":[50],"attempt":[51],"mitigate":[53],"errors":[55],"but":[56],"typically":[57],"rely":[58],"on":[59],"scalar":[60],"scoring,":[61],"which":[62],"lacks":[63],"explanatory":[65],"power":[66],"necessary":[67],"diagnose":[69],"complex":[70],"misconceptions.In":[72],"this":[73],"work,":[74],"we":[75,102],"introduce":[76],"PhysPRM,":[77],"Generative":[79],"PRM":[80],"that":[81,127,148],"treats":[82],"evaluation":[83],"generative":[86],"task":[87],"produce":[89],"fine-grained":[90],"diagnoses":[91],"comprising":[92],"critiques,":[93],"final":[94],"judgments,":[95],"specific":[97],"error":[98],"types.To":[99],"facilitate":[100],"this,":[101],"develop":[103],"an":[104],"automated":[105],"data":[106],"synthesis":[107],"pipeline":[108],"construct":[110],"PhysPRM30K,":[111],"comprehensive":[113],"training":[114,125],"dataset,":[115],"PhysProcessBench,":[117],"rigorously":[119],"human-verified":[120],"benchmark.By":[121],"employing":[122],"two-stage":[124],"paradigm":[126],"integrates":[128],"Supervised":[129],"Fine-Tuning":[130],"Group":[132],"Relative":[133],"Policy":[134],"Optimization,":[135],"PhysPRM":[136,149],"significantly":[137],"enhances":[138],"capabilities":[142],"various":[144],"LLMs.Extensive":[145],"experiments":[146],"demonstrate":[147],"boosts":[150],"performance":[151],"by":[152],"up":[153],"8.9":[155],"10.3":[157],"points":[158],"Best-of-N":[160],"critique":[162],"refinement":[163],"strategies,":[164],"respectively.":[165]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}