{"id":"https://openalex.org/W7125937303","doi":"https://doi.org/10.1109/smc58881.2025.11343701","title":"DMA-MCTS: Dynamic Memory-Augmented Monte-Carlo Tree Search for LLM Task Planning","display_name":"DMA-MCTS: Dynamic Memory-Augmented Monte-Carlo Tree Search for LLM Task Planning","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125937303","doi":"https://doi.org/10.1109/smc58881.2025.11343701"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5025921778","display_name":"Jia Wang","orcid":"https://orcid.org/0000-0002-3110-3892"},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiakang Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China,100190","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124107179","display_name":"Qi Wang","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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China,100190","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124138867","display_name":"Mengxian Li","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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxian Li","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China,100190","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124086195","display_name":"Tingting Li","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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingting Li","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China,100190","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027459729","display_name":"Yan Xu","orcid":"https://orcid.org/0000-0003-0379-8866"},"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/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjun Xu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Computing Technology,Beijing,China,100190","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025921778"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87201325,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6377","last_page":"6382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.6302000284194946,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.6302000284194946,"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":0.13109999895095825,"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"}},{"id":"https://openalex.org/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.05169999971985817,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/task","display_name":"Task (project management)","score":0.5961999893188477},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.5863999724388123},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5231999754905701},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5110999941825867},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4828999936580658},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.47929999232292175},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4733999967575073},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.46070000529289246}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7833999991416931},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5961999893188477},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.5863999724388123},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5231999754905701},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5110999941825867},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.491100013256073},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.47929999232292175},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4733999967575073},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.46070000529289246},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.44850000739097595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4471000134944916},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27950000762939453},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2126316555","https://openalex.org/W2168359464","https://openalex.org/W2799002257","https://openalex.org/W4383097638","https://openalex.org/W4389520747","https://openalex.org/W4393147158","https://openalex.org/W4393160302"],"related_works":[],"abstract_inverted_index":{"While":[0],"Large":[1],"Language":[2],"Models":[3],"(LLMs)":[4],"show":[5],"promise":[6],"for":[7,190],"task":[8,167],"planning,":[9,62],"their":[10],"efficacy":[11],"diminishes":[12],"in":[13,26,52,164],"complex,":[14],"long-horizon":[15,201],"tasks":[16,148],"within":[17,149],"dynamic,":[18],"partially":[19],"observable":[20],"environments,":[21],"primarily":[22],"due":[23],"to":[24,120,131],"challenges":[25,51],"long-term":[27],"reasoning":[28],"and":[29,89,123,138,172,186,194],"effective":[30,195],"adaptation":[31],"from":[32,135],"experience.":[33],"A":[34],"key":[35],"limitation":[36],"of":[37,44,55,107,166,181,199],"current":[38],"approaches":[39],"is":[40],"the":[41,53,150,178],"insufficient":[42],"utilization":[43],"historical":[45,118],"trajectory":[46],"information.":[47],"To":[48],"overcome":[49],"these":[50],"context":[54],"Partially":[56],"Observable":[57],"Markov":[58],"Decision":[59],"Process":[60],"(POMDP)":[61],"this":[63],"paper":[64],"introduces":[65],"DMA-MCTS":[66,155],"(Dynamic":[67],"Memory-Augmented":[68],"Monte-Carlo":[69],"Tree":[70,78],"Search),":[71],"a":[72,85,98,111,125],"framework":[73],"that":[74,154],"integrates":[75],"Monte":[76],"Carlo":[77],"Search":[79],"(MCTS)":[80],"with":[81],"LLMs,":[82],"augmented":[83],"by":[84,117],"novel":[86],"dynamic":[87,184],"memory":[88,101,185],"reflection":[90,127,188],"system.":[91],"The":[92],"core":[93],"technical":[94],"contributions":[95],"include:":[96],"(1)":[97],"dual-layer":[99],"semantic":[100],"repository":[102],"enabling":[103],"efficient":[104],"context-aware":[105],"retrieval":[106],"past":[108],"experiences;":[109],"(2)":[110],"memory-enhanced":[112],"UCT":[113],"selection":[114],"strategy":[115],"biased":[116],"Q-values":[119],"guide":[121],"search;":[122],"(3)":[124],"differentiated":[126],"mechanism":[128],"employing":[129],"LLMs":[130],"extract":[132],"generalizable":[133],"knowledge":[134],"both":[136],"successful":[137],"failed":[139],"trajectories.":[140],"Comprehensive":[141],"evaluations":[142],"conducted":[143],"on":[144],"complex":[145],"object":[146],"rearrangement":[147],"VirtualHome":[151],"simulator":[152],"demonstrate":[153],"significantly":[156],"outperforms":[157],"relevant":[158],"baselines,":[159],"including":[160],"standard":[161],"LLM-MCTS":[162],"approaches,":[163],"terms":[165],"success":[168],"rate,":[169],"generalization":[170],"capabilities,":[171],"planning":[173,202],"efficiency.":[174],"These":[175],"results":[176],"underscore":[177],"critical":[179],"importance":[180],"integrating":[182],"structured":[183],"systematic":[187],"mechanisms":[189],"developing":[191],"highly":[192],"adaptive":[193],"LLM-based":[196],"agents":[197],"capable":[198],"tackling":[200],"problems.":[203]},"counts_by_year":[],"updated_date":"2026-01-29T23:17:01.242718","created_date":"2026-01-29T00:00:00"}