{"id":"https://openalex.org/W7154287659","doi":"https://doi.org/10.1016/j.neucom.2026.133642","title":"Efficient multi-agent policy learning using knowledge distillation of large language models","display_name":"Efficient multi-agent policy learning using knowledge distillation of large language models","publication_year":2026,"publication_date":"2026-04-14","ids":{"openalex":"https://openalex.org/W7154287659","doi":"https://doi.org/10.1016/j.neucom.2026.133642"},"language":"en","primary_location":{"id":"doi:10.1016/j.neucom.2026.133642","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133642","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063763076","display_name":"Liqiang Tian","orcid":"https://orcid.org/0009-0004-8053-7859"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liqiang Tian","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0004-8053-7859","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133626717","display_name":"Peiliang Wu","orcid":"https://orcid.org/0000-0003-1228-2757"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peiliang Wu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1228-2757","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133626072","display_name":"Qian Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian Zhang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0004-2867-7512","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103275250","display_name":"Bingyi Mao","orcid":"https://orcid.org/0009-0008-6547-5150"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bingyi Mao","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0008-6547-5150","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133589446","display_name":"Wenbai Chen","orcid":"https://orcid.org/0000-0001-7683-2776"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenbai Chen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-7683-2776","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5063763076"],"corresponding_institution_ids":[],"apc_list":{"value":2470,"currency":"USD","value_usd":2470},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78472838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"685","issue":null,"first_page":"133642","last_page":"133642"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.20239999890327454,"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":0.20239999890327454,"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/T10028","display_name":"Topic Modeling","score":0.1143999993801117,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.08720000088214874,"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/policy-learning","display_name":"Policy learning","score":0.6017000079154968},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4424999952316284},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4034000039100647},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.33390000462532043},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.27090001106262207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918000221252441},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.630299985408783},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.6017000079154968},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5407000184059143},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4424999952316284},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31470000743865967},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C32254414","wikidata":"https://www.wikidata.org/wiki/Q4724364","display_name":"Algorithmic learning theory","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.neucom.2026.133642","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133642","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1331161382","display_name":null,"funder_award_id":"U20A20167","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1484327127","display_name":null,"funder_award_id":"62276028","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G453775460","display_name":null,"funder_award_id":"F202103079","funder_id":"https://openalex.org/F4320322163","funder_display_name":"Natural Science Foundation of Hebei Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322163","display_name":"Natural Science Foundation of Hebei Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W3196869853","https://openalex.org/W4283582213","https://openalex.org/W4388033982","https://openalex.org/W4389352485","https://openalex.org/W4389671046","https://openalex.org/W4389941392","https://openalex.org/W4394828156","https://openalex.org/W4396877948","https://openalex.org/W4399451670","https://openalex.org/W4399693807"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2026-04-15T00:00:00"}