{"id":"https://openalex.org/W7160922016","doi":"https://doi.org/10.48550/arxiv.2605.08503","title":"NARRA-Gym for Evaluating Interactive Narrative Agents","display_name":"NARRA-Gym for Evaluating Interactive Narrative Agents","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160922016","doi":"https://doi.org/10.48550/arxiv.2605.08503"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2605.08503","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.08503","pdf_url":"https://arxiv.org/pdf/2605.08503","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2605.08503","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135949404","display_name":"Yue Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132683133","display_name":"Yuchen Ma","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Yuchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135263765","display_name":"Jiayi Ye","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Jiayi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135960875","display_name":"Wenjie Wang","orcid":"https://orcid.org/0009-0007-2739-0618","observed_orcids":["https://orcid.org/0009-0007-2739-0618"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wenjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132771723","display_name":"Zipeng Ling","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ling, Zipeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135947045","display_name":"Xingjian Hu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Xingjian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004826137","display_name":"Yuexing Hao","orcid":"https://orcid.org/0000-0003-4375-7655","observed_orcids":["https://orcid.org/0000-0003-4375-7655"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao, Yuexing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104078124","display_name":"Zichen Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zichen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135947974","display_name":"Zhangchen Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Zhangchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135990453","display_name":"Yunhong He","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Yunhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124940452","display_name":"Zhengqing Yuan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Zhengqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139352854","display_name":"Yujun Zhou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yujun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070509358","display_name":"Kehan Guo","orcid":"https://orcid.org/0009-0004-6396-1869","observed_orcids":["https://orcid.org/0009-0004-6396-1869"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Kehan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135958840","display_name":"Chaoran Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Chaoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135363169","display_name":"Toby Jia-Jun Li","orcid":"https://orcid.org/0000-0001-7902-7625","observed_orcids":["https://orcid.org/0000-0001-7902-7625"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Toby Jia-Jun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081442873","display_name":"Stefan Feuerriegel","orcid":"https://orcid.org/0000-0001-7856-8729","observed_orcids":["https://orcid.org/0000-0001-7856-8729","https://orcid.org/0000-0001-7982-611X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feuerriegel, Stefan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000755750","display_name":"Xiangliang Zhang","orcid":"https://orcid.org/0000-0002-3574-5665","observed_orcids":["https://orcid.org/0000-0002-3574-5665"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiangliang","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9394999742507935,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9394999742507935,"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/T12031","display_name":"Speech and dialogue systems","score":0.029100000858306885,"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/T12461","display_name":"Narrative Theory and Analysis","score":0.006599999964237213,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/interactive-storytelling","display_name":"interactive storytelling","score":0.7870000004768372},{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.5960000157356262},{"id":"https://openalex.org/keywords/benchmark-environments","display_name":"benchmark environments","score":0.5389999747276306},{"id":"https://openalex.org/keywords/memory-updating","display_name":"memory updating","score":0.4180000126361847},{"id":"https://openalex.org/keywords/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.8709999918937683}],"concepts":[{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.7620000243186951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6622999906539917},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6251999735832214},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.6098999977111816},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5784000158309937},{"id":"https://openalex.org/C313442","wikidata":"https://www.wikidata.org/wiki/Q778556","display_name":"Persona","level":2,"score":0.5755000114440918},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4438000023365021},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34380000829696655},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.31459999084472656},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3059999942779541},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.29339998960494995},{"id":"https://openalex.org/C201025465","wikidata":"https://www.wikidata.org/wiki/Q11248500","display_name":"User experience design","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2712000012397766},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C24845683","wikidata":"https://www.wikidata.org/wiki/Q178651","display_name":"Interview","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C11189718","wikidata":"https://www.wikidata.org/wiki/Q218152","display_name":"User story","level":4,"score":0.25270000100135803},{"id":"https://openalex.org/C117893075","wikidata":"https://www.wikidata.org/wiki/Q6966213","display_name":"Narrative inquiry","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2605.08503","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.08503","pdf_url":"https://arxiv.org/pdf/2605.08503","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2605.08503","doi":"https://doi.org/10.48550/arxiv.2605.08503","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08503","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2605.08503","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.08503","pdf_url":"https://arxiv.org/pdf/2605.08503","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7202171566","https://openalex.org/W7213253035","https://openalex.org/W4387355423","https://openalex.org/W4406530625","https://openalex.org/W4411119177","https://openalex.org/W4415798012","https://openalex.org/W4410121929","https://openalex.org/W4381104068","https://openalex.org/W4413322025","https://openalex.org/W7125786419"],"abstract_inverted_index":{"Interactive":[0],"narrative":[1,154],"tasks":[2],"require":[3],"LLMs":[4,102],"to":[5,13],"sustain":[6],"a":[7,14,70,75,104,113,156],"coherent,":[8],"evolving":[9],"story":[10,35,48,78,87,167],"while":[11],"adapting":[12],"user":[15,144],"over":[16,108],"multiple":[17],"turns.":[18],"However,":[19],"suitable":[20],"benchmarks":[21],"for":[22,159],"this":[23],"setting":[24],"are":[25],"limited:":[26],"existing":[27],"evaluations":[28],"often":[29],"focus":[30],"on":[31,142],"static":[32],"prompts,":[33],"isolated":[34,166],"generations,":[36],"or":[37,146],"post-hoc":[38],"ratings,":[39],"and":[40,52,58,80,94,112,131],"therefore":[41],"miss":[42],"whether":[43],"models":[44,134],"can":[45,139],"jointly":[46],"manage":[47],"generation,":[49],"long-context":[50],"state":[51],"pacing,":[53],"character":[54],"simulation,":[55],"empathic":[56],"personalization,":[57],"story-grounded":[59],"artifacts.":[60],"We":[61,98],"introduce":[62],"NARRA-Gym,":[63],"an":[64],"executable":[65],"evaluation":[66,115,132],"environment":[67],"that":[68,135,152],"turns":[69],"sparse":[71],"emotional":[72],"seed":[73],"into":[74],"complete":[76],"interactive":[77,153],"episode":[79],"logs":[81],"the":[82],"full":[83],"model-in-the-loop":[84],"trajectory,":[85],"including":[86],"construction,":[88],"memory":[89],"updates,":[90],"planning,":[91],"pacing":[92],"interventions,":[93],"optional":[95],"artifact":[96],"synthesis.":[97],"evaluate":[99],"nine":[100],"frontier":[101],"using":[103],"controlled":[105],"LLM-as-judge":[106],"sweep":[107],"eight":[109],"benchmark":[110,158],"personas":[111],"human":[114],"in":[116],"which":[117],"participants":[118],"rate":[119],"customized":[120],"model":[121],"outputs.":[122],"Our":[123],"results":[124],"show":[125],"substantial":[126],"variation":[127],"across":[128],"models,":[129],"personas,":[130],"dimensions:":[133],"produce":[136],"fluent":[137],"stories":[138],"still":[140],"fail":[141],"robustness,":[143],"experience,":[145],"resistance-sensitive":[147],"personalization.":[148],"These":[149],"findings":[150],"suggest":[151],"offers":[155],"useful":[157],"evaluating":[160],"long-horizon,":[161],"user-adaptive":[162],"LLM":[163],"behavior":[164],"beyond":[165],"quality.":[168]},"counts_by_year":[],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2026-05-13T00:00:00"}
