{"id":"https://openalex.org/W4412945066","doi":"https://doi.org/10.18653/v1/2025.acl-long.857","title":"Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents","display_name":"Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945066","doi":"https://doi.org/10.18653/v1/2025.acl-long.857"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.857","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.857","pdf_url":"https://aclanthology.org/2025.acl-long.857.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.857.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013651593","display_name":"Tianyi Men","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyi Men","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002351083","display_name":"Zhuoran Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuoran Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101759357","display_name":"Pengfei Cao","orcid":"https://orcid.org/0000-0003-4443-1892"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengfei Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074010547","display_name":"Yubo Chen","orcid":"https://orcid.org/0009-0000-1197-0959"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yubo Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037558598","display_name":"Kang Liu","orcid":"https://orcid.org/0000-0002-8413-123X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026425886","display_name":"Jun Zhao","orcid":"https://orcid.org/0009-0005-2920-7448"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Zhao","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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17521","last_page":"17541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.8029999732971191,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.8029999732971191,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.7605999708175659,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.7360000014305115,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7862457633018494},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6767037510871887},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5537013411521912},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47776854038238525},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.40680745244026184},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3532567024230957},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13350650668144226},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.07333195209503174}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7862457633018494},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6767037510871887},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5537013411521912},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47776854038238525},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40680745244026184},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3532567024230957},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13350650668144226},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.07333195209503174},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.857","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.857","pdf_url":"https://aclanthology.org/2025.acl-long.857.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.857","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.857","pdf_url":"https://aclanthology.org/2025.acl-long.857.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":[{"score":0.5299999713897705,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G5208670511","display_name":null,"funder_award_id":"U24A20335","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/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335892","display_name":"Youth Innovation Promotion Association","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945066.pdf","grobid_xml":"https://content.openalex.org/works/W4412945066.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"As":[0],"Multimodal":[1],"Large":[2],"Language":[3],"Models":[4],"(MLLMs)":[5],"advance,":[6],"multimodal":[7,171],"agents":[8,30],"show":[9,173],"promise":[10],"in":[11,23,86,182],"real-world":[12,99],"tasks":[13],"like":[14],"web":[15],"navigation":[16],"and":[17,34,98,106,139,143,157],"embodied":[18],"intelligence.However,":[19],"due":[20],"to":[21,39,53,64,81,153,160],"limitations":[22],"a":[24,66,78,126,129],"lack":[25],"of":[26,118,125,133,164],"external":[27,44],"feedback,":[28,45],"these":[29,73],"struggle":[31],"with":[32,108],"self-correction":[33],"generalization.A":[35],"promising":[36],"approach":[37],"is":[38,48,60,89,186],"use":[40],"reward":[41,55,67,83,112,184],"models":[42,56,172],"as":[43],"but":[46],"there":[47,59],"no":[49],"clear":[50],"on":[51],"how":[52],"select":[54],"for":[57,115,179],"agents.Thus,":[58],"an":[61],"urgent":[62],"need":[63,178],"build":[65],"bench":[68],"targeted":[69],"at":[70,121,188],"agents.To":[71],"address":[72],"challenges,":[74,156],"we":[75],"propose":[76],"Agent-RewardBench,":[77],"benchmark":[79,88],"designed":[80],"evaluate":[82],"modeling":[84],"ability":[85],"MLLMs.The":[87],"characterized":[90],"by":[91],"three":[92],"key":[93],"features:":[94],"(1)":[95],"Multiple":[96],"dimensions":[97],"agent":[100,119,183],"scenarios":[101],"evaluation.It":[102,113],"covers":[103],"perception,":[104],"planning,":[105],"safety":[107],"7":[109],"scenarios;":[110],"(2)Step-level":[111],"allows":[114],"the":[116,122,136,162,165,177],"assessment":[117],"capabilities":[120],"individual":[123],"steps":[124],"task,":[127],"providing":[128],"more":[130],"granular":[131],"view":[132],"performance":[134],"during":[135],"planning":[137],"process;":[138],"(3)":[140],"Appropriately":[141],"difficulty":[142,151],"highquality.We":[144],"carefully":[145],"sample":[146],"from":[147],"10":[148],"diverse":[149],"models,":[150],"control":[152],"maintain":[154],"task":[155],"manual":[158],"verification":[159],"ensure":[161],"integrity":[163],"data.Experiments":[166],"demonstrate":[167],"that":[168],"even":[169],"state-of-the-art":[170],"limited":[174],"performance,":[175],"highlighting":[176],"specialized":[180],"training":[181],"modeling.Code":[185],"available":[187],"github.":[189]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}