{"id":"https://openalex.org/W4387432128","doi":"https://doi.org/10.48550/arxiv.2310.03249","title":"Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning","display_name":"Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning","publication_year":2023,"publication_date":"2023-10-05","ids":{"openalex":"https://openalex.org/W4387432128","doi":"https://doi.org/10.48550/arxiv.2310.03249"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.03249","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.03249","pdf_url":"https://arxiv.org/pdf/2310.03249","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.03249","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061950213","display_name":"Mohamed Aghzal","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aghzal, Mohamed","raw_affiliation_strings":["Department of Computer Science George Mason University Fairfax , VA , 22030 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science George Mason University Fairfax , VA , 22030 , USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017823298","display_name":"Erion Plaku","orcid":"https://orcid.org/0000-0001-5605-4575","observed_orcids":["https://orcid.org/0000-0001-5605-4575","https://orcid.org/0000-0002-6622-386X"]},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Plaku, Erion","raw_affiliation_strings":["Department of Computer Science George Mason University Fairfax , VA , 22030 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science George Mason University Fairfax , VA , 22030 , USA","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101616607","display_name":"Ziyu Yao","orcid":"https://orcid.org/0009-0007-4571-3505","observed_orcids":["https://orcid.org/0009-0007-4571-3505"]},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yao, Ziyu","raw_affiliation_strings":["Department of Computer Science George Mason University Fairfax , VA , 22030 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science George Mason University Fairfax , VA , 22030 , USA","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162714631"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"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":0.524399995803833,"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":0.524399995803833,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.17599999904632568,"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":0.10689999908208847,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9150000214576721},{"id":"https://openalex.org/keywords/path-planning","display_name":"path planning","score":0.9959999918937683},{"id":"https://openalex.org/keywords/spatio-temporal-reasoning","display_name":"spatio-temporal reasoning","score":0.953000009059906},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.5099999904632568},{"id":"https://openalex.org/keywords/gpt-4","display_name":"GPT-4","score":0.7329999804496765},{"id":"https://openalex.org/keywords/few-shot-prompting","display_name":"few-shot prompting","score":0.9539999961853027},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"obstacle avoidance","score":0.8330000042915344},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.7590000033378601}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.9044973850250244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5309144258499146},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5103644728660583},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.43306106328964233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33910441398620605},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.1452244520187378},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07968267798423767},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07191932201385498}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.03249","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.03249","pdf_url":"https://arxiv.org/pdf/2310.03249","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,"listed_in":[],"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.2310.03249","doi":"https://doi.org/10.48550/arxiv.2310.03249","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.03249","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.03249","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.03249","pdf_url":"https://arxiv.org/pdf/2310.03249","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387432128.pdf","grobid_xml":"https://content.openalex.org/works/W4387432128.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7212141075","https://openalex.org/W4412638939","https://openalex.org/W7140073999","https://openalex.org/W7165686884","https://openalex.org/W4408451202","https://openalex.org/W4402385945","https://openalex.org/W4399912408","https://openalex.org/W4414968317","https://openalex.org/W4403676730","https://openalex.org/W4416036380"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"achieved":[5,136],"remarkable":[6],"success":[7],"across":[8],"a":[9,39],"wide":[10],"spectrum":[11],"of":[12,32,96,107],"tasks;":[13],"however,":[14],"they":[15,143],"still":[16,124],"face":[17],"limitations":[18],"in":[19,34,110],"scenarios":[20],"that":[21,60],"demand":[22],"long-term":[23,128],"planning":[24],"and":[25,72,94,119],"spatial":[26,111],"reasoning.":[27,130],"To":[28],"facilitate":[29],"this":[30,35,77],"line":[31],"research,":[33],"work,":[36],"we":[37,79],"propose":[38],"new":[40],"benchmark,":[41,78],"termed":[42],"$\\textbf{P}$ath":[43],"$\\textbf{P}$lanning":[44],"from":[45],"$\\textbf{N}$atural":[46],"$\\textbf{L}$anguage":[47],"($\\textbf{PPNL}$).":[48],"Our":[49,101],"benchmark":[50],"evaluates":[51],"LLMs'":[52],"spatial-temporal":[53],"reasoning":[54,141],"by":[55],"formulating":[56],"''path":[57],"planning''":[58],"tasks":[59],"require":[61],"an":[62],"LLM":[63],"to":[64,66,74,117,126,145,147],"navigate":[65],"target":[67],"locations":[68],"while":[69,133],"avoiding":[70],"obstacles":[71],"adhering":[73],"constraints.":[75],"Leveraging":[76],"systematically":[80],"investigate":[81],"LLMs":[82,135],"including":[83],"GPT-4":[84,109],"via":[85,99],"different":[86],"few-shot":[87,108],"prompting":[88],"methodologies":[89],"as":[90,92],"well":[91],"BART":[93],"T5":[95],"various":[97],"sizes":[98],"fine-tuning.":[100],"experimental":[102],"results":[103,138],"show":[104],"the":[105],"promise":[106],"reasoning,":[112],"when":[113],"it":[114,123],"is":[115],"prompted":[116],"reason":[118],"act":[120],"interleavedly,":[121],"although":[122],"fails":[125],"perform":[127],"temporal":[129],"In":[131],"contrast,":[132],"fine-tuned":[134],"impressive":[137],"on":[139],"in-distribution":[140],"tasks,":[142],"struggled":[144],"generalize":[146],"larger":[148],"environments":[149,151],"or":[150],"with":[152],"more":[153],"obstacles.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2023-10-09T00:00:00"}