{"id":"https://openalex.org/W4404609238","doi":"https://doi.org/10.1109/icmlca63499.2024.10754169","title":"Dual-Agent Multi-Hop Reasoning Based on Reward Shaping and Action Dropout","display_name":"Dual-Agent Multi-Hop Reasoning Based on Reward Shaping and Action Dropout","publication_year":2024,"publication_date":"2024-10-18","ids":{"openalex":"https://openalex.org/W4404609238","doi":"https://doi.org/10.1109/icmlca63499.2024.10754169"},"language":"en","primary_location":{"id":"doi:10.1109/icmlca63499.2024.10754169","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icmlca63499.2024.10754169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 5th International Conference on Machine Learning and Computer Application (ICMLCA)","raw_type":"proceedings-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/A5023126624","display_name":"Qiyue Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiyue Sun","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633735","display_name":"Yongli Wang","orcid":"https://orcid.org/0000-0003-2219-067X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongli Wang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100417626","display_name":"Dongmei Liu","orcid":"https://orcid.org/0000-0003-1645-3998"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongmei Liu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023126624"],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1895076,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"150","last_page":"154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.8299000263214111,"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/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.8299000263214111,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8083000183105469,"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/computer-science","display_name":"Computer science","score":0.7293424606323242},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.7173517346382141},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.709431529045105},{"id":"https://openalex.org/keywords/hop","display_name":"Hop (telecommunications)","score":0.5047436952590942},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.45128968358039856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39643436670303345},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2953682541847229},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2123594582080841}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7293424606323242},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.7173517346382141},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.709431529045105},{"id":"https://openalex.org/C25906391","wikidata":"https://www.wikidata.org/wiki/Q1432381","display_name":"Hop (telecommunications)","level":2,"score":0.5047436952590942},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.45128968358039856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39643436670303345},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2953682541847229},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2123594582080841},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmlca63499.2024.10754169","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icmlca63499.2024.10754169","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 5th International Conference on Machine Learning and Computer Application (ICMLCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3082178636","https://openalex.org/W2782041652","https://openalex.org/W2612657834","https://openalex.org/W2392157706","https://openalex.org/W2599192953","https://openalex.org/W1987310671","https://openalex.org/W2117210722","https://openalex.org/W2952088488","https://openalex.org/W1521968289","https://openalex.org/W4225691210"],"abstract_inverted_index":{"The":[0],"dual-agent":[1,84],"multi-hop":[2,85],"reasoning":[3,18,86,110],"method":[4,23,87],"addresses":[5],"the":[6,26,32,35,39,55,70,99,115,132,168],"issue":[7],"of":[8,72,172],"target":[9,58],"entity":[10],"omission":[11],"in":[12,101],"single-agent":[13],"systems":[14],"caused":[15],"by":[16,65,105,124],"increased":[17],"path":[19],"length.":[20],"However,":[21],"this":[22,80],"still":[24],"has":[25],"following":[27],"challenges:":[28],"First,":[29],"even":[30],"if":[31],"agent":[33],"finds":[34],"correct":[36],"answer":[37,153],"within":[38],"knowledge":[40],"graph,":[41],"it":[42,45],"may":[43,62],"misclassify":[44],"as":[46,54],"incorrect":[47],"due":[48],"to":[49,69,113,130,135,160],"training":[50],"set":[51],"limitations,":[52],"known":[53],"false":[56,73,120,140],"negative":[57],"problem.":[59],"Second,":[60],"agents":[61],"be":[63],"misled":[64],"erroneous":[66],"paths,":[67,137],"leading":[68],"creation":[71],"positive":[74,141],"paths.":[75,142],"To":[76],"tackle":[77],"these":[78],"issues,":[79],"paper":[81],"proposes":[82],"a":[83,126],"based":[88],"on":[89],"Reward":[90],"Shaping":[91],"and":[92,118,122,151,170,175],"Action":[93],"Dropout":[94],"(RADAM).":[95],"This":[96],"approach":[97],"improves":[98],"model":[100],"two":[102],"ways:":[103],"(1)":[104],"introducing":[106],"an":[107],"embedding-based":[108],"single-hop":[109],"model,":[111],"TransE,":[112],"optimize":[114],"reward":[116,173],"function":[117],"reduce":[119],"negatives;":[121],"(2)":[123],"incorporating":[125],"random":[127],"masking":[128],"mechanism":[129],"diminish":[131],"agent's":[133],"sensitivity":[134],"spurious":[136],"thereby":[138],"reducing":[139],"Experimental":[143],"results":[144],"demonstrate":[145],"that":[146],"RADAM":[147],"achieves":[148],"more":[149],"accurate":[150],"efficient":[152],"retrieval":[154],"across":[155],"most":[156],"benchmark":[157],"datasets":[158],"compared":[159],"baseline":[161],"algorithms,":[162],"with":[163],"ablation":[164],"experiments":[165],"further":[166],"confirming":[167],"effectiveness":[169],"synergy":[171],"shaping":[174],"action":[176],"dropout.":[177]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}