{"id":"https://openalex.org/W4399912408","doi":"https://doi.org/10.48550/arxiv.2406.13094","title":"Exploring and Benchmarking the Planning Capabilities of Large Language Models","display_name":"Exploring and Benchmarking the Planning Capabilities of Large Language Models","publication_year":2024,"publication_date":"2024-06-18","ids":{"openalex":"https://openalex.org/W4399912408","doi":"https://doi.org/10.48550/arxiv.2406.13094"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.13094","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.13094","pdf_url":"https://arxiv.org/pdf/2406.13094","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.13094","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066427994","display_name":"Bernd Bohnet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bohnet, Bernd","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053888839","display_name":"Azade Nova","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nova, Azade","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113069812","display_name":"Aaron Parisi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Parisi, Aaron T","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026208886","display_name":"Kevin Swersky","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Swersky, Kevin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098954587","display_name":"Katayoon Goshvadi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goshvadi, Katayoon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040269658","display_name":"Hanjun Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Hanjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010575626","display_name":"Dale Schuurmans","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schuurmans, Dale","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087591662","display_name":"Noah Fiedel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fiedel, Noah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5045805879","display_name":"Hanie Sedghi","orcid":"https://orcid.org/0000-0002-7163-5009"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sedghi, Hanie","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":true,"cited_by_count":1,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9769999980926514,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9769999980926514,"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":0.9054999947547913,"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/benchmarking","display_name":"Benchmarking","score":0.8775975704193115},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5325291156768799},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.26338693499565125},{"id":"https://openalex.org/keywords/marketing","display_name":"Marketing","score":0.05687043070793152}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8775975704193115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5325291156768799},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.26338693499565125},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.05687043070793152}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.13094","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.13094","pdf_url":"https://arxiv.org/pdf/2406.13094","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.13094","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.13094","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.13094","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.13094","pdf_url":"https://arxiv.org/pdf/2406.13094","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399912408.pdf","grobid_xml":"https://content.openalex.org/works/W4399912408.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687"],"abstract_inverted_index":{"Classical":[0],"and":[1,41,63,89,140,150],"natural":[2,42],"language":[3,13,43],"planning":[4,25,39,91,105,119,142],"tasks":[5,54],"remain":[6],"a":[7,32],"difficult":[8],"domain":[9],"for":[10,23,61],"modern":[11],"large":[12],"models":[14],"(LLMs).":[15],"In":[16,93],"this":[17],"work,":[18],"we":[19,30,70,95,122,145],"lay":[20],"the":[21,72,83,97,110,124,127,134],"foundations":[22],"improving":[24],"capabilities":[26],"of":[27,53,58,66,74,100,112,126],"LLMs.":[28],"First,":[29],"construct":[31],"comprehensive":[33],"benchmark":[34],"suite":[35,46],"encompassing":[36],"both":[37],"classical":[38],"benchmarks":[40],"scenarios.":[44],"This":[45],"includes":[47],"algorithms":[48],"to":[49,78,116,136,138],"methodically":[50],"generate":[51],"instances":[52],"with":[55],"varying":[56],"levels":[57],"difficulty,":[59],"allowing":[60],"rigorous":[62],"systematic":[64],"evaluation":[65],"LLM":[67,80,118],"performance.":[68,92,120],"Next,":[69],"investigate":[71,146],"use":[73],"many-shot":[75],"in-context":[76],"learning":[77],"enhance":[79],"planning,":[81],"exploring":[82],"relationship":[84],"between":[85],"increased":[86],"context":[87],"length":[88],"improved":[90],"addition,":[94],"demonstrate":[96],"positive":[98],"impact":[99],"fine-tuning":[101],"LLMs":[102],"on":[103],"optimal":[104],"paths.":[106],"We":[107],"also":[108],"probe":[109,123],"efficacy":[111],"chain-of-thought":[113],"reasoning":[114],"methods":[115,129],"improve":[117],"Moreover,":[121],"performance":[125],"proposed":[128],"in":[130],"out-of-distribution":[131],"scenarios,":[132],"assessing":[133],"ability":[135],"generalize":[137],"novel":[139],"unseen":[141],"challenges.":[143],"Finally,":[144],"model's":[147],"failure":[148],"modes":[149],"reveal":[151],"insights":[152],"that":[153],"hold":[154],"true":[155],"across":[156],"different":[157],"benchmarks.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2024-06-22T00:00:00"}