{"id":"https://openalex.org/W7138437458","doi":"https://doi.org/10.1609/aaai.v40i32.39931","title":"VORTEX: Aligning Task Utility and Human Preferences Through LLM-Guided Reward Shaping","display_name":"VORTEX: Aligning Task Utility and Human Preferences Through LLM-Guided Reward Shaping","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138437458","doi":"https://doi.org/10.1609/aaai.v40i32.39931"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i32.39931","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i32.39931","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39931/43892","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39931/43892","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129693912","display_name":"Guojun Xiong","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guojun Xiong","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120595272","display_name":"Milind Tambe","orcid":null},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milind Tambe","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.3,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"32","first_page":"27162","last_page":"27170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.23489999771118164,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.23489999771118164,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.1535000056028366,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.042399998754262924,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/task","display_name":"Task (project management)","score":0.6969000101089478},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.6402000188827515},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5388000011444092},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46889999508857727},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.3874000012874603},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.385699987411499},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.37770000100135803},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.3630000054836273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7386000156402588},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6969000101089478},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6402000188827515},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5388000011444092},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46889999508857727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45010000467300415},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.3874000012874603},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.385699987411499},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3630000054836273},{"id":"https://openalex.org/C117035363","wikidata":"https://www.wikidata.org/wiki/Q3769299","display_name":"Human behavior","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C205706631","wikidata":"https://www.wikidata.org/wiki/Q2319304","display_name":"Expected utility hypothesis","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3249000012874603},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.32109999656677246},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3179999887943268},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.3156000077724457},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C52820260","wikidata":"https://www.wikidata.org/wiki/Q7551312","display_name":"Social preferences","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.258899986743927}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i32.39931","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i32.39931","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39931/43892","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i32.39931","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i32.39931","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/39931/43892","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4814641773700714,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138437458.pdf","grobid_xml":"https://content.openalex.org/works/W7138437458.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,62],"social":[1],"impact":[2],"optimization,":[3,89],"AI":[4],"decision":[5,111],"systems":[6],"often":[7],"rely":[8],"on":[9,99],"solvers":[10,18,118],"that":[11,73,127,145],"optimize":[12],"well-calibrated":[13],"mathematical":[14],"objectives.":[15],"However,":[16],"these":[17],"cannot":[19],"directly":[20],"accommodate":[21],"evolving":[22],"human":[23,81],"preferences,":[24],"typically":[25],"expressed":[26],"in":[27,140,149],"natural":[28,114,174],"language":[29,41,115],"rather":[30],"than":[31],"formal":[32],"constraints.":[33],"Recent":[34],"approaches":[35],"address":[36],"this":[37,63],"by":[38,173],"using":[39],"large":[40],"models":[42],"(LLMs)":[43],"to":[44,93,109,130],"generate":[45,95],"new":[46],"reward":[47,70],"functions":[48],"from":[49],"preference":[50,136],"descriptions.":[51],"While":[52],"flexible,":[53],"they":[54],"risk":[55],"sacrificing":[56],"the":[57,85],"system's":[58],"core":[59],"utility":[60,134],"guarantees.":[61],"paper,":[64],"we":[65,90],"propose":[66],"VORTEX,":[67],"a":[68,162],"language-guided":[69],"shaping":[71,96],"framework":[72],"preserves":[74],"established":[75],"optimization":[76,171],"goals":[77,153],"while":[78,154],"adaptively":[79],"incorporating":[80],"feedback.":[82],"By":[83],"formalizing":[84],"problem":[86],"as":[87],"multi-objective":[88],"use":[91],"LLMs":[92],"iteratively":[94],"rewards":[97],"based":[98],"verbal":[100],"reinforcement":[101],"and":[102,135,164],"text-gradient":[103],"prompt":[104],"updates.":[105],"This":[106,159],"allows":[107],"stakeholders":[108],"steer":[110],"behavior":[112],"via":[113],"without":[116],"modifying":[117],"or":[119],"specifying":[120],"trade-off":[121],"weights.":[122],"We":[123],"provide":[124],"theoretical":[125],"guarantees":[126],"VORTEX":[128,146],"converges":[129],"Pareto-optimal":[131],"trade-offs":[132],"between":[133],"satisfaction.":[137],"Empirical":[138],"results":[139],"real-world":[141],"allocation":[142],"tasks":[143],"demonstrate":[144],"outperforms":[147],"baselines":[148],"satisfying":[150],"human-aligned":[151],"coverage":[152],"maintaining":[155],"high":[156],"task":[157],"performance.":[158],"work":[160],"introduces":[161],"practical":[163],"theoretically":[165],"grounded":[166],"paradigm":[167],"for":[168],"human-AI":[169],"collaborative":[170],"guided":[172],"language.":[175]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}