{"id":"https://openalex.org/W7124469460","doi":"https://doi.org/10.48550/arxiv.2601.10148","title":"DecisionLLM: Large Language Models for Long Sequence Decision Exploration","display_name":"DecisionLLM: Large Language Models for Long Sequence Decision Exploration","publication_year":2026,"publication_date":"2026-01-15","ids":{"openalex":"https://openalex.org/W7124469460","doi":"https://doi.org/10.48550/arxiv.2601.10148"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.10148","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.10148","pdf_url":"https://arxiv.org/pdf/2601.10148","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.10148","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123203686","display_name":"Xiaowei Lv","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]},{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Lv, Xiaowei","raw_affiliation_strings":["Renmin University of China , Beijing China","Work is done during the internship at Alibaba Group "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China , Beijing China","institution_ids":["https://openalex.org/I78988378"]},{"raw_affiliation_string":"Work is done during the internship at Alibaba Group ","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123242213","display_name":"Zhilin Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Zhilin","raw_affiliation_strings":["Alibaba Group , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group , Beijing , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123208968","display_name":"Yijun Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yijun","raw_affiliation_strings":["Alibaba Group , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group , Beijing , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102722801","display_name":"Yusen Huo","orcid":"https://orcid.org/0009-0006-8863-3209","observed_orcids":["https://orcid.org/0009-0006-8863-3209"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huo, Yusen","raw_affiliation_strings":["Alibaba Group , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group , Beijing , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070212683","display_name":"Song Ju","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ju, Siyuan","raw_affiliation_strings":["Alibaba Group , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group , Beijing , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023010974","display_name":"Xuyan Li","orcid":"https://orcid.org/0009-0004-8489-4765","observed_orcids":["https://orcid.org/0009-0004-8489-4765"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Xuyan","raw_affiliation_strings":["Alibaba Group , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group , Beijing , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123198321","display_name":"Chunxiang Hong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong, Chunxiang","raw_affiliation_strings":["Alibaba Group , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group , Beijing , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143446680","display_name":"Tianyu Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Tianyu","raw_affiliation_strings":["Alibaba Group , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group , Beijing , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123191979","display_name":"Yongcai Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Yongcai","raw_affiliation_strings":["Renmin University of China , Beijing China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Renmin University of China , Beijing China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123250717","display_name":"Peng Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun, Peng","raw_affiliation_strings":["Alibaba Group , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group , Beijing , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123189561","display_name":"Chuan Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Chuan","raw_affiliation_strings":["Alibaba Group , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group , Beijing , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123187461","display_name":"Jian Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Jian","raw_affiliation_strings":["Alibaba Group , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group , Beijing , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5141013088","display_name":"Bo Zheng","orcid":"https://orcid.org/0009-0001-4007-3955","observed_orcids":["https://orcid.org/0009-0001-4007-3955"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng, Bo","raw_affiliation_strings":["Alibaba Group , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group , Beijing , China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9911999702453613,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9911999702453613,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0034000000450760126,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0012000000569969416,"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/large-language-models","display_name":"large language models","score":0.8859999775886536},{"id":"https://openalex.org/keywords/decision-transformer","display_name":"decision transformer","score":0.8690000176429749},{"id":"https://openalex.org/keywords/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":0.6880000233650208},{"id":"https://openalex.org/keywords/real-time-bidding","display_name":"real-time bidding","score":0.7919999957084656},{"id":"https://openalex.org/keywords/computational-advertising","display_name":"computational advertising","score":0.875},{"id":"https://openalex.org/keywords/scaling-laws","display_name":"scaling laws","score":0.890999972820282},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.7440000176429749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573999762535095},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573999762535095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5863999724388123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5863999724388123},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5615000128746033},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5615000128746033},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5375999808311462},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5375999808311462},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5210000276565552},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5210000276565552},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C9233905","wikidata":"https://www.wikidata.org/wiki/Q3276328","display_name":"Bidding","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C9233905","wikidata":"https://www.wikidata.org/wiki/Q3276328","display_name":"Bidding","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42250001430511475},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.42250001430511475},{"id":"https://openalex.org/C169087156","wikidata":"https://www.wikidata.org/wiki/Q2131593","display_name":"Framing (construction)","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C169087156","wikidata":"https://www.wikidata.org/wiki/Q2131593","display_name":"Framing (construction)","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.359499990940094},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.359499990940094},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C97508593","wikidata":"https://www.wikidata.org/wiki/Q1359069","display_name":"Contingency","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C97508593","wikidata":"https://www.wikidata.org/wiki/Q1359069","display_name":"Contingency","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C39891107","wikidata":"https://www.wikidata.org/wiki/Q5767098","display_name":"Hinge loss","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C39891107","wikidata":"https://www.wikidata.org/wiki/Q5767098","display_name":"Hinge loss","level":3,"score":0.27630001306533813},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.10148","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.10148","pdf_url":"https://arxiv.org/pdf/2601.10148","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2601.10148","doi":"https://doi.org/10.48550/arxiv.2601.10148","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.10148","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.10148","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.10148","pdf_url":"https://arxiv.org/pdf/2601.10148","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7124469460.pdf","grobid_xml":"https://content.openalex.org/works/W7124469460.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2173248099","https://openalex.org/W2736601468","https://openalex.org/W2788741142","https://openalex.org/W2995706821","https://openalex.org/W3034786558","https://openalex.org/W3096964654","https://openalex.org/W3111981703","https://openalex.org/W3122543654","https://openalex.org/W3205794883","https://openalex.org/W4291960900","https://openalex.org/W4399695759","https://openalex.org/W4402667093","https://openalex.org/W4413943474","https://openalex.org/W4415025005","https://openalex.org/W4415133730","https://openalex.org/W4415337225"],"related_works":["https://openalex.org/W4404782565","https://openalex.org/W4387929115","https://openalex.org/W4403346622","https://openalex.org/W7134048292","https://openalex.org/W7172483416","https://openalex.org/W7160901391","https://openalex.org/W6910510183","https://openalex.org/W7160596331","https://openalex.org/W4385763700","https://openalex.org/W4417433115"],"abstract_inverted_index":{"Long-sequence":[0],"decision-making,":[1],"which":[2,65],"is":[3,10,107],"usually":[4],"addressed":[5],"through":[6],"reinforcement":[7],"learning":[8,146],"(RL),":[9],"a":[11,33,74,119,142,164,172],"critical":[12],"component":[13],"for":[14,233],"optimizing":[15],"strategic":[16],"operations":[17],"in":[18,25,54,84,104,236],"dynamic":[19],"environments,":[20],"such":[21],"as":[22,39,116,131,141],"real-time":[23],"bidding":[24,199],"computational":[26],"advertising.":[27],"The":[28],"Decision":[29,210],"Transformer":[30,69,211],"(DT)":[31,212],"introduced":[32],"powerful":[34],"paradigm":[35,227],"by":[36,213,219],"framing":[37],"RL":[38],"an":[40],"autoregressive":[41],"sequence":[42],"modeling":[43],"problem.":[44,88],"Concurrently,":[45],"Large":[46],"Language":[47],"Models":[48],"(LLMs)":[49],"have":[50],"demonstrated":[51],"remarkable":[52],"success":[53],"complex":[55],"reasoning":[56],"and":[57,125,191,198,218,228],"planning":[58],"tasks.":[59,100],"This":[60,89],"inspires":[61],"us":[62],"whether":[63],"LLMs,":[64],"share":[66],"the":[67,92,108,208,225],"same":[68],"foundation,":[70],"but":[71],"operate":[72],"at":[73],"much":[75],"larger":[76],"scale,":[77,188],"can":[78,158],"unlock":[79],"new":[80],"levels":[81],"of":[82,94,122,174],"performance":[83,182],"long-horizon":[85],"sequential":[86],"decision-making":[87],"work":[90],"investigates":[91],"application":[93],"LLMs":[95],"to":[96,112,147,230],"offline":[97,195],"decision":[98],"making":[99],"A":[101],"fundamental":[102],"challenge":[103],"this":[105,178],"domain":[106],"LLMs'":[109],"inherent":[110],"inability":[111],"interpret":[113],"continuous":[114],"values,":[115],"they":[117],"lack":[118],"native":[120],"understanding":[121],"numerical":[123],"magnitude":[124],"order":[126],"when":[127],"values":[128],"are":[129],"represented":[130],"text":[132],"strings.":[133],"To":[134],"address":[135],"this,":[136],"we":[137,167],"propose":[138],"treating":[139],"trajectories":[140],"distinct":[143],"modality.":[144],"By":[145],"align":[148],"trajectory":[149],"data":[150,189,192],"with":[151],"natural":[152],"language":[153],"task":[154],"descriptions,":[155],"our":[156],"model":[157,187],"autoregressively":[159],"predict":[160],"future":[161,234],"decisions":[162],"within":[163],"cohesive":[165],"framework":[166],"term":[168],"DecisionLLM.":[169],"We":[170],"establish":[171],"set":[173],"scaling":[175],"laws":[176],"governing":[177],"paradigm,":[179],"demonstrating":[180],"that":[181],"hinges":[183],"on":[184,215,221],"three":[185],"factors:":[186],"volume,":[190],"quality.":[193],"In":[194],"experimental":[196],"benchmarks":[197],"scenarios,":[200],"DecisionLLM":[201],"achieves":[202],"strong":[203],"performance.":[204],"Specifically,":[205],"DecisionLLM-3B":[206],"outperforms":[207],"traditional":[209],"69.4":[214],"Maze2D":[216],"umaze-v1":[217],"0.085":[220],"AuctionNet.":[222],"It":[223],"extends":[224],"AIGB":[226],"points":[229],"promising":[231],"directions":[232],"exploration":[235],"online":[237],"bidding.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-01-17T00:00:00"}