{"id":"https://openalex.org/W7166869401","doi":"https://doi.org/10.18653/v1/2026.acl-long.1062","title":"Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling","display_name":"Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166869401","doi":"https://doi.org/10.18653/v1/2026.acl-long.1062"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1062","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1062","pdf_url":"https://aclanthology.org/2026.acl-long.1062.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 64th 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/2026.acl-long.1062.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139768210","display_name":"Jiaxuan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaxuan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139795083","display_name":"Yulan Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yulan Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113478430","display_name":"Wenjin Yang","orcid":"https://orcid.org/0000-0003-1166-899X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjin Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139809799","display_name":"Zheng Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng Pan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139737226","display_name":"Xin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139778005","display_name":"Lan-Zhe Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lan-Zhe Guo","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":0.8581498,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23174","last_page":"23200"},"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":0.21140000224113464,"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":0.21140000224113464,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.1889999955892563,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.14079999923706055,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4616999924182892},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.30169999599456787},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2777999937534332},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.2549000084400177},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2531999945640564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6233000159263611},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4616999924182892},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37560001015663147},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2531999945640564},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2493000030517578},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24740000069141388},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.24729999899864197}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1062","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1062","pdf_url":"https://aclanthology.org/2026.acl-long.1062.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1062","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1062","pdf_url":"https://aclanthology.org/2026.acl-long.1062.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8577097480","display_name":null,"funder_award_id":"BK20243012","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166869401.pdf","grobid_xml":"https://content.openalex.org/works/W7166869401.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"classical":[1],"Reinforcement":[2],"Learning":[3],"from":[4],"Human":[5],"Feedback":[6],"(RLHF),":[7],"Reward":[8],"Models":[9,22],"(RMs)":[10],"serve":[11],"as":[12,174],"the":[13,41,162],"fundamental":[14],"signal":[15],"provider":[16],"for":[17,64,164,184],"model":[18],"alignment.As":[19],"Large":[20],"Language":[21],"evolve":[23],"into":[24],"agentic":[25,186],"systems":[26],"capable":[27],"of":[28,43,141],"autonomous":[29],"tool":[30],"invocation":[31],"and":[32,93,101,112,121,134,137,180],"complex":[33,76],"reasoning,":[34],"reward":[35,170],"modeling":[36],"faces":[37],"a":[38,60,124,176,181],"key":[39],"challenge:":[40],"lack":[42],"benchmarks":[44],"specifically":[45],"designed":[46],"to":[47],"assess":[48],"RM":[49],"capabilities":[50],"in":[51,75,167],"toolintegrated":[52],"environments.To":[53],"address":[54],"this":[55],"gap,":[56],"we":[57],"present":[58],"Plan-RewardBench,":[59],"trajectorylevel":[61],"preference":[62,188],"benchmark":[63,116],"evaluating":[65],"how":[66],"well":[67],"judges":[68],"distinguish":[69],"preferred":[70],"versus":[71],"distractor":[72],"agent":[73],"trajectories":[74,100],"tool-using":[77],"scenarios.Plan-RewardBench":[78],"covers":[79],"four":[80],"representative":[81,117],"task":[82,135],"families-(i)":[83],"Safety":[84],"Refusal,":[85],"(ii)":[86],"Tool-Irrelevance":[87],"/":[88],"Unavailability,":[89],"(iii)":[90],"Complex":[91],"Planning,":[92],"(iv)":[94],"Robust":[95],"Error":[96],"Recoverywith":[97],"validated":[98],"positive":[99],"confusable":[102],"hard":[103],"negatives":[104],"constructed":[105],"via":[106],"multimodel":[107],"natural":[108],"rollouts,":[109],"rule-based":[110],"perturbations,":[111],"minimal-edit":[113],"LLM":[114],"perturbations.We":[115],"RMs":[118],"(generative,":[119],"discriminative,":[120],"LLM-as-Judge)":[122],"under":[123],"unified":[125],"pairwise":[126],"protocol,":[127],"reporting":[128],"accuracy":[129],"trends":[130],"across":[131],"trajectory":[132],"lengths":[133],"categories,":[136],"providing":[138],"diagnostic":[139],"analyses":[140],"prevalent":[142],"failure":[143],"modes.Results":[144],"show":[145],"that":[146],"all":[147],"three":[148],"evaluator":[149],"families":[150],"face":[151],"substantial":[152],"challenges,":[153],"with":[154],"performance":[155],"degrading":[156],"sharply":[157],"on":[158],"long-horizon":[159],"trajectories,":[160],"underscoring":[161],"need":[163],"specialized":[165],"training":[166],"agentic,":[168],"trajectory-level":[169],"modeling.Ultimately,":[171],"Plan-RewardBench":[172],"serves":[173],"both":[175],"practical":[177],"evaluation":[178],"suite":[179],"reusable":[182],"blueprint":[183],"constructing":[185],"planning":[187],"data.":[189]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}