{"id":"https://openalex.org/W4402352495","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650094","title":"RRdE: A Decision Making Framework for Language Agents in Interactive Environments","display_name":"RRdE: A Decision Making Framework for Language Agents in Interactive Environments","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352495","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650094"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5080423762","display_name":"Xufeng Zhou","orcid":"https://orcid.org/0000-0002-3153-6954"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xufeng Zhou","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004618782","display_name":"Linjing Li","orcid":"https://orcid.org/0000-0002-8737-099X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linjing Li","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111319841","display_name":"Daniel Dajun Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daniel Dajun Zeng","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9980999827384949,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9980999827384949,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9970999956130981,"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/T12031","display_name":"Speech and dialogue systems","score":0.9944000244140625,"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":0.7048950791358948},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.48588865995407104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7048950791358948},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.48588865995407104}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650094","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650094","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2121700581","https://openalex.org/W2751936342","https://openalex.org/W2810346659","https://openalex.org/W2913668833","https://openalex.org/W2998557583","https://openalex.org/W3099204253","https://openalex.org/W4226316256","https://openalex.org/W4237040408","https://openalex.org/W4353112996","https://openalex.org/W4366999541","https://openalex.org/W4378505261","https://openalex.org/W4385571466","https://openalex.org/W4385573990","https://openalex.org/W4386528753","https://openalex.org/W4386644471","https://openalex.org/W4387835442","https://openalex.org/W4392669753","https://openalex.org/W4393065402","https://openalex.org/W4393147158","https://openalex.org/W4396723768","https://openalex.org/W6640571240","https://openalex.org/W6719647531","https://openalex.org/W6772190580","https://openalex.org/W6784429693","https://openalex.org/W6801063103","https://openalex.org/W6811273590","https://openalex.org/W6846254642","https://openalex.org/W6849732303","https://openalex.org/W6849843017","https://openalex.org/W6851275496","https://openalex.org/W6851896007","https://openalex.org/W6852748447","https://openalex.org/W6853465110"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Large":[0],"language":[1],"models(LLMs)":[2],"have":[3],"demonstrated":[4],"remarkable":[5],"planning":[6,94,102,115],"and":[7,48,71,75,86,101,117,122,150,182,194,206],"reasoning":[8,98,133],"abilities,":[9],"particularly":[10],"as":[11,32,59],"few-shot":[12,176],"learners,":[13],"when":[14,30,52],"utilizing":[15],"in-context":[16],"learning.":[17],"However,":[18],"since":[19],"LLMs":[20,61],"are":[21],"not":[22],"grounded":[23],"during":[24,88],"training,":[25],"they":[26],"still":[27],"encounter":[28],"difficulties":[29],"acting":[31],"agents":[33],"in":[34,43,104,174,179,192,201,210],"tasks":[35,191,209,215],"that":[36,45],"require":[37],"interaction":[38,69],"with":[39,54,216],"the":[40,65,83,113,124,137,155,159,175,202],"environment,":[41],"especially":[42],"scenarios":[44],"involve":[46],"long-term":[47,114,125,166],"multistep":[49],"interactions.":[50],"Even":[51],"provided":[53],"a":[55,90,130,146,217],"complete":[56],"game":[57],"trajectory":[58],"context,":[60],"struggle":[62],"to":[63,157],"comprehend":[64],"meaning":[66],"of":[67,120,188,199,220],"each":[68],"step,":[70],"may":[72],"easily":[73],"hallucinate":[74],"fail.":[76],"To":[77],"address":[78],"these":[79],"challenges,":[80],"we":[81],"introduce":[82],"RRdE":[84,109,170],"(Reasoning":[85],"Replanning":[87],"Exploration),":[89],"framework":[91],"inspired":[92],"by":[93,141,165],"theories,":[95],"designed":[96],"for":[97],"about":[99],"actions":[100],"subgoals":[103],"complex":[105,205],"interactive":[106],"environments.":[107],"The":[108],"method":[110],"can":[111],"integrate":[112],"ability":[116,119],"tooluse":[118],"LLMs,":[121],"transform":[123],"sequential":[126],"decision":[127],"problem":[128,163],"into":[129],"relatively":[131],"simple":[132],"problem,":[134],"thereby":[135],"reducing":[136],"error":[138],"behavior":[139],"caused":[140,164],"excessive":[142],"context.":[143],"We":[144],"devise":[145],"reflection-based":[147],"goal":[148,167],"decomposition":[149],"replanning":[151],"scheme,":[152],"which":[153],"enables":[154],"agent":[156],"overcome":[158],"strict":[160],"sub-goal":[161],"dependency":[162],"planning.":[168],"Consequently,":[169],"achieves":[171],"state-of-the-art":[172],"performance":[173],"learning":[177],"setting":[178],"both":[180],"AlfWorld":[181],"ScienceWorld":[183],"environments,":[184],"accomplishing":[185],"132":[186],"out":[187],"134":[189],"test":[190],"AlfWorld,":[193],"obtaining":[195],"an":[196],"average":[197],"score":[198,219],"82.16":[200],"30":[203],"more":[204],"challenging":[207],"scientific":[208],"ScienceWorld,":[211],"successfully":[212],"completing":[213],"7":[214],"full":[218],"100.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}