{"id":"https://openalex.org/W7166862171","doi":"https://doi.org/10.18653/v1/2026.findings-acl.95","title":"Exploring Reasoning Reward Model for Agents","display_name":"Exploring Reasoning Reward Model for Agents","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166862171","doi":"https://doi.org/10.18653/v1/2026.findings-acl.95"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.95","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.95","pdf_url":"https://aclanthology.org/2026.findings-acl.95.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.95.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139772380","display_name":"Kaixuan Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaixuan Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139787831","display_name":"Kaituo Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaituo Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139735868","display_name":"Manyuan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manyuan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114139333","display_name":"Tianshuo Peng","orcid":"https://orcid.org/0009-0009-7347-0648"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianshuo Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045905018","display_name":"Zhixun Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhixun Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102370506","display_name":"Yilei Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yilei Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443505","display_name":"Shuang Chen","orcid":"https://orcid.org/0000-0002-9053-8845"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuang Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078165161","display_name":"Xiangyu Yue","orcid":"https://orcid.org/0000-0002-6887-2046"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangyu Yue","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":0.8507022,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1975","last_page":"1991"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.12870000302791595,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.12870000302791595,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.07119999825954437,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.0357000008225441,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.6071000099182129},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5863999724388123},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.438400000333786},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.4230000078678131},{"id":"https://openalex.org/keywords/opportunistic-reasoning","display_name":"Opportunistic reasoning","score":0.3840999901294708},{"id":"https://openalex.org/keywords/qualitative-reasoning","display_name":"Qualitative reasoning","score":0.3515999913215637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6449999809265137},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6071000099182129},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5863999724388123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49950000643730164},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.438400000333786},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.4230000078678131},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.3840999901294708},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36250001192092896},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C2992562121","wikidata":"https://www.wikidata.org/wiki/Q3817808","display_name":"Scientific reasoning","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.3149000108242035},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.95","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.95","pdf_url":"https://aclanthology.org/2026.findings-acl.95.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.95","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.95","pdf_url":"https://aclanthology.org/2026.findings-acl.95.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/G3917743038","display_name":null,"funder_award_id":"8115074","funder_id":"https://openalex.org/F4320335138","funder_display_name":"Shun Hing Institute of Advanced Engineering"},{"id":"https://openalex.org/G8285413768","display_name":null,"funder_award_id":"62306261","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation 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/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"},{"id":"https://openalex.org/F4320322942","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48"},{"id":"https://openalex.org/F4320335138","display_name":"Shun Hing Institute of Advanced Engineering","ror":"https://ror.org/00t33hh48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166862171.pdf","grobid_xml":"https://content.openalex.org/works/W7166862171.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Agentic":[0],"Reinforcement":[1],"Learning":[2],"(Agentic":[3],"RL)":[4],"has":[5],"achieved":[6],"notable":[7],"success":[8],"in":[9],"enabling":[10],"agents":[11],"to":[12,31,37,145],"perform":[13],"complex":[14],"reasoning":[15,34,65,78,133],"and":[16,80,103,124,136,140],"tool":[17],"use.However,":[18],"most":[19],"methods":[20],"still":[21],"relies":[22],"on":[23,122,126],"sparse":[24],"outcome-based":[25],"reward":[26,52,134],"for":[27,58],"training.Such":[28],"feedback":[29,57,106],"fails":[30],"differentiate":[32],"intermediate":[33],"quality,":[35],"leading":[36],"suboptimal":[38],"training":[39,137],"results.In":[40],"this":[41],"paper,":[42],"we":[43,91],"introduce":[44],"Agent":[45],"Reasoning":[46],"Reward":[47],"Model":[48],"(Agent-RRM),":[49],"a":[50,69],"multifaceted":[51],"model":[53,135],"that":[54,72,85,114],"produces":[55],"structured":[56],"agentic":[59],"trajectories,":[60],"including":[61],"(1)":[62],"an":[63,82],"explicit":[64],"trace":[66],",":[67],"(2)":[68],"focused":[70],"critique":[71],"provides":[73],"refinement":[74],"guidance":[75],"by":[76],"highlighting":[77],"flaws,":[79],"(3)":[81],"overall":[83],"score":[84],"evaluates":[86],"process":[87],"performance.Leveraging":[88],"these":[89],"signals,":[90],"systematically":[92],"investigate":[93],"three":[94],"integration":[95],"strategies:":[96],"Reagent-C":[97],"(text-augmented":[98],"refinement),":[99],"Reagent-R":[100],"(reward-augmented":[101],"guidance),":[102],"Reagent-U":[104,115],"(unified":[105],"integration).Extensive":[107],"evaluations":[108],"across":[109],"12":[110],"diverse":[111],"benchmarks":[112],"demonstrate":[113],"yields":[116],"substantial":[117],"performance":[118],"leaps,":[119],"achieving":[120],"43.7%":[121],"GAIA":[123],"46.2%":[125],"WebWalkerQA,":[127],"validating":[128],"the":[129],"effectiveness":[130],"of":[131],"our":[132],"schemes.Code,":[138],"models,":[139],"datasets":[141],"will":[142],"be":[143],"released":[144],"facilitate":[146],"future":[147],"research.":[148]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}