{"id":"https://openalex.org/W7136522018","doi":"https://doi.org/10.48550/arxiv.2603.12740","title":"ToolTree: Efficient LLM Agent Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning","display_name":"ToolTree: Efficient LLM Agent Tool Planning via Dual-Feedback Monte Carlo Tree Search and Bidirectional Pruning","publication_year":2026,"publication_date":"2026-03-13","ids":{"openalex":"https://openalex.org/W7136522018","doi":"https://doi.org/10.48550/arxiv.2603.12740"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.12740","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.12740","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.12740","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129534550","display_name":"Shuo Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Shuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129638267","display_name":"Soyeon Caren Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Soyeon Caren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129614134","display_name":"Yihao Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Yihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122608055","display_name":"Shuhe Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shuhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129633532","display_name":"Eduard Hoy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoy, Eduard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10028","display_name":"Topic Modeling","score":0.3296000063419342,"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/T10028","display_name":"Topic Modeling","score":0.3296000063419342,"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":0.13410000503063202,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.0640999972820282,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.7998999953269958},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5928999781608582},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.5709999799728394},{"id":"https://openalex.org/keywords/futures-studies","display_name":"Futures studies","score":0.5496000051498413},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.4503999948501587},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.3686999976634979},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.34619998931884766}],"concepts":[{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7998999953269958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7192999720573425},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5928999781608582},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.5709999799728394},{"id":"https://openalex.org/C64848388","wikidata":"https://www.wikidata.org/wiki/Q188867","display_name":"Futures studies","level":2,"score":0.5496000051498413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5494999885559082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48660001158714294},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.4503999948501587},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34619998931884766},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2639999985694885},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2606000006198883},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.12740","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.12740","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.12740","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.12740","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Model":[2],"(LLM)":[3],"agents":[4],"are":[5],"increasingly":[6],"applied":[7],"to":[8,42,83,135],"complex,":[9],"multi-step":[10],"tasks":[11,112],"that":[12,37,79,117],"require":[13],"interaction":[14],"with":[15],"diverse":[16],"external":[17],"tools":[18],"across":[19,105],"various":[20],"domains.":[21],"However,":[22],"current":[23],"LLM":[24,73],"agent":[25,82],"tool":[26,34,62,67,101,110],"planning":[27,59,111,138],"methods":[28],"typically":[29],"rely":[30],"on":[31,113],"greedy,":[32],"reactive":[33],"selection":[35],"strategies":[36],"lack":[38],"foresight":[39],"and":[40,75,98,108],"fail":[41],"account":[43],"for":[44,61],"inter-tool":[45],"dependencies.":[46],"In":[47],"this":[48],"paper,":[49],"we":[50],"present":[51],"ToolTree,":[52],"a":[53,71],"novel":[54],"Monte":[55],"Carlo":[56],"tree":[57],"search-inspired":[58],"paradigm":[60],"planning.":[63],"ToolTree":[64,118],"explores":[65],"possible":[66],"usage":[68],"trajectories":[69],"using":[70],"dual-stage":[72],"evaluation":[74],"bidirectional":[76],"pruning":[77,93],"mechanism":[78],"enables":[80],"the":[81,100,124,136],"make":[84],"informed,":[85],"adaptive":[86],"decisions":[87],"over":[88],"extended":[89],"tool-use":[90],"sequences":[91],"while":[92,122],"less":[94],"promising":[95],"branches":[96],"before":[97],"after":[99],"execution.":[102],"Empirical":[103],"evaluations":[104],"both":[106],"open-set":[107],"closed-set":[109],"4":[114],"benchmarks":[115],"demonstrate":[116],"consistently":[119],"improves":[120],"performance":[121],"keeping":[123],"highest":[125],"efficiency,":[126],"achieving":[127],"an":[128],"average":[129],"gain":[130],"of":[131],"around":[132],"10\\%":[133],"compared":[134],"state-of-the-art":[137],"paradigm.":[139]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-17T00:00:00"}