{"id":"https://openalex.org/W4412944949","doi":"https://doi.org/10.18653/v1/2025.acl-long.945","title":"AgentRM: Enhancing Agent Generalization with Reward Modeling","display_name":"AgentRM: Enhancing Agent Generalization with Reward Modeling","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944949","doi":"https://doi.org/10.18653/v1/2025.acl-long.945"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.945","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.945","pdf_url":"https://aclanthology.org/2025.acl-long.945.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.945.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100374652","display_name":"Yu Xia","orcid":"https://orcid.org/0009-0003-9800-1051"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Xia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jingru Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingru Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025388406","display_name":"Weize Chen","orcid":"https://orcid.org/0009-0007-5882-8870"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weize Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065035408","display_name":"Siyu Yan","orcid":"https://orcid.org/0009-0006-2993-321X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siyu Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100546036","display_name":"Xin Cong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Cong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350979","display_name":"Zhong Zhang","orcid":"https://orcid.org/0009-0008-7584-057X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060320299","display_name":"Yue Lu","orcid":"https://orcid.org/0000-0001-9111-5943"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaxi Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043098453","display_name":"Yankai Lin","orcid":"https://orcid.org/0000-0002-0151-6178"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yankai Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320723","display_name":"Zhiyuan Liu","orcid":"https://orcid.org/0000-0002-7709-2543"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyuan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5046448314","display_name":"Maosong Sun","orcid":"https://orcid.org/0000-0002-6011-6115"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maosong Sun","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":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19277","last_page":"19290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.9531000256538391,"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/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.9531000256538391,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.919700026512146,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9175999760627747,"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/generalization","display_name":"Generalization","score":0.7250978350639343},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6275919675827026},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3249126076698303},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11155766248703003}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7250978350639343},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6275919675827026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3249126076698303},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11155766248703003},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.945","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.945","pdf_url":"https://aclanthology.org/2025.acl-long.945.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.945","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.945","pdf_url":"https://aclanthology.org/2025.acl-long.945.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944949.pdf","grobid_xml":"https://content.openalex.org/works/W4412944949.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W3162204513","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Yu":[0],"Xia,":[1],"Jingru":[2],"Fan,":[3],"Weize":[4],"Chen,":[5],"Siyu":[6],"Yan,":[7],"Xin":[8],"Cong,":[9],"Zhong":[10],"Zhang,":[11],"Yaxi":[12],"Lu,":[13],"Yankai":[14],"Lin,":[15],"Zhiyuan":[16],"Liu,":[17],"Maosong":[18],"Sun.":[19],"Proceedings":[20],"of":[21,26],"the":[22,27],"63rd":[23],"Annual":[24],"Meeting":[25],"Association":[28],"for":[29],"Computational":[30],"Linguistics":[31],"(Volume":[32],"1:":[33],"Long":[34],"Papers).":[35],"2025.":[36]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
