{"id":"https://openalex.org/W7138125510","doi":"https://doi.org/10.1609/aaai.v40i35.40201","title":"Think, Speak, Decide: Language-Augmented Multi-Agent Reinforcement Learning for Economic Decision-Making","display_name":"Think, Speak, Decide: Language-Augmented Multi-Agent Reinforcement Learning for Economic Decision-Making","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138125510","doi":"https://doi.org/10.1609/aaai.v40i35.40201"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i35.40201","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i35.40201","pdf_url":null,"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://doi.org/10.1609/aaai.v40i35.40201","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Heyang Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Heyang Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Qirui Mi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qirui Mi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Qipeng Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qipeng Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zijun Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zijun Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Bo Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Haifeng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haifeng Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30640535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"35","first_page":"29582","last_page":"29590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.12479999661445618,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.12479999661445618,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.07329999655485153,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05490000173449516,"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/ambiguity","display_name":"Ambiguity","score":0.7836999893188477},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.715399980545044},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6633999943733215},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.46140000224113464},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.3529999852180481},{"id":"https://openalex.org/keywords/economic-model","display_name":"Economic model","score":0.32359999418258667}],"concepts":[{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7836999893188477},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.715399980545044},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6804999709129333},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6633999943733215},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.46140000224113464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4368000030517578},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.3529999852180481},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33059999346733093},{"id":"https://openalex.org/C119693030","wikidata":"https://www.wikidata.org/wiki/Q2180497","display_name":"Economic model","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C2986080485","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision maker","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C109332788","wikidata":"https://www.wikidata.org/wiki/Q615445","display_name":"Economic efficiency","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C9114305","wikidata":"https://www.wikidata.org/wiki/Q1428317","display_name":"Situational ethics","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i35.40201","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i35.40201","pdf_url":null,"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.v40i35.40201","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i35.40201","pdf_url":null,"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":0.7239552140235901,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Economic":[0],"decision\u2011making":[1],"depends":[2],"not":[3],"only":[4],"on":[5,13,95],"structured":[6],"signals\u2014such":[7],"as":[8],"prices":[9],"and":[10,19,40,80,90,110,130,141,155],"taxes\u2014but":[11],"also":[12],"unstructured":[14],"language,":[15],"including":[16],"peer":[17,102],"dialogue":[18],"media":[20],"narratives.":[21],"While":[22],"multi\u2011agent":[23],"reinforcement":[24],"learning":[25],"(MARL)":[26],"has":[27],"shown":[28],"promise":[29],"in":[30,121,133],"optimizing":[31],"economic":[32,58,122,157],"decisions,":[33],"it":[34],"struggles":[35],"with":[36],"the":[37,51,61,96,146],"semantic":[38],"ambiguity":[39],"contextual":[41],"richness":[42],"of":[43,148],"language.":[44],"We":[45],"propose":[46],"LAMP":[47,66,126],"(Language\u2011Augmented":[48],"Multi\u2011Agent":[49],"Policy),":[50],"first":[52],"framework":[53],"to":[54,63,76,116,151],"integrate":[55],"language":[56],"into":[57,112],"decision\u2011making,":[59],"narrowing":[60],"gap":[62],"real\u2011world":[64],"settings.":[65],"follows":[67],"a":[68,113],"Think\u2013Speak\u2013Decide":[69],"pipeline:":[70],"(1)":[71],"Think":[72],"interprets":[73],"numerical":[74,107],"observations":[75],"extract":[77],"short\u2011term":[78],"shocks":[79],"long\u2011term":[81],"trends,":[82],"caching":[83],"high\u2011value":[84],"reasoning":[85],"trajectories.":[86],"(2)":[87],"Speak":[88],"crafts":[89],"exchanges":[91],"strategic":[92],"messages":[93],"based":[94],"reasoning,":[97,109],"updating":[98],"beliefs":[99],"by":[100],"parsing":[101],"communications.":[103],"(3)":[104],"Decide":[105],"fuses":[106],"data,":[108],"reflections":[111],"MARL":[114,129],"policy":[115],"optimize":[117],"language\u2011augmented":[118,149],"decision\u2011making.":[119],"Experiments":[120],"simulation":[123],"show":[124],"that":[125],"outperforms":[127],"both":[128],"LLM\u2011only":[131],"baselines":[132],"cumulative":[134],"return":[135],"(+63.5%,":[136],"+34.0%),":[137],"robustness":[138],"(+18.8%,":[139],"+59.4%),":[140],"interpretability.":[142],"These":[143],"results":[144],"demonstrate":[145],"potential":[147],"policies":[150],"deliver":[152],"more":[153],"effective":[154],"robust":[156],"strategies.":[158]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-12T00:00:00"}