{"id":"https://openalex.org/W7162606545","doi":null,"title":"GroupTravelBench: Benchmarking LLM Agents on Multi-Person Travel Planning","display_name":"GroupTravelBench: Benchmarking LLM Agents on Multi-Person Travel Planning","publication_year":2026,"publication_date":"2026-05-24","ids":{"openalex":"https://openalex.org/W7162606545"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2605.25200","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.25200","pdf_url":"https://arxiv.org/pdf/2605.25200","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2605.25200","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137110321","display_name":"Xiang Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137140808","display_name":"Yulan Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Yulan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030659566","display_name":"Lulu Zheng","orcid":"https://orcid.org/0000-0001-7688-6096"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Lulu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137158949","display_name":"Zheng Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137101555","display_name":"Xin Li","orcid":"https://orcid.org/0000-0001-9598-0299"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137169961","display_name":"Yong Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yong","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":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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.1881999969482422,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.1881999969482422,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.09619999676942825,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.094200000166893,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7940000295639038},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7347000241279602},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5720999836921692},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5151000022888184},{"id":"https://openalex.org/keywords/ticket","display_name":"Ticket","score":0.4453999996185303},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.39309999346733093},{"id":"https://openalex.org/keywords/sandbox","display_name":"Sandbox (software development)","score":0.3910999894142151},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3508000075817108}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7940000295639038},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7347000241279602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7113000154495239},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5720999836921692},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5151000022888184},{"id":"https://openalex.org/C2776540713","wikidata":"https://www.wikidata.org/wiki/Q7800647","display_name":"Ticket","level":2,"score":0.4453999996185303},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C167981075","wikidata":"https://www.wikidata.org/wiki/Q2667186","display_name":"Sandbox (software development)","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.3824000060558319},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C44210515","wikidata":"https://www.wikidata.org/wiki/Q16968978","display_name":"Bespoke","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C51485801","wikidata":"https://www.wikidata.org/wiki/Q16966861","display_name":"Efficient frontier","level":3,"score":0.31150001287460327},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.29420000314712524},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C539828613","wikidata":"https://www.wikidata.org/wiki/Q178512","display_name":"Public transport","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2502000033855438},{"id":"https://openalex.org/C144072006","wikidata":"https://www.wikidata.org/wiki/Q4462116","display_name":"Travel behavior","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2605.25200","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.25200","pdf_url":"https://arxiv.org/pdf/2605.25200","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2605.25200","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.25200","pdf_url":"https://arxiv.org/pdf/2605.25200","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Travel":[0],"planning":[1,35],"in":[2,93],"the":[3,23,55,65,107,173],"real":[4,75],"world":[5],"is":[6,25,194],"overwhelmingly":[7],"a":[8,19,94,153,166,195],"\\textit{group}":[9],"activity,":[10],"yet":[11],"existing":[12],"LLM":[13,200],"travel-planning":[14,201],"benchmarks":[15,115],"reduce":[16],"it":[17,83],"to":[18,58],"single":[20],"user,":[21],"where":[22],"field":[24],"approaching":[26],"saturation.":[27],"This":[28],"single-user":[29,114],"assumption":[30],"sidesteps":[31],"what":[32],"makes":[33],"group":[34,145],"hard":[36],"for":[37,68,102,199],"an":[38],"agent:":[39],"discovering":[40],"private":[41,126],"preferences":[42,127],"across":[43,87],"multiple":[44],"users,":[45],"surfacing":[46],"conflicts,":[47],"and":[48,80,110,140,161],"balancing":[49],"utility":[50,146],"against":[51,147],"fairness.":[52,148],"To":[53],"bring":[54],"task":[56],"back":[57],"its":[59],"multi-user":[60],"reality,":[61],"we":[62],"introduce":[63],"\\textbf{\\textit{GroupTravelBench}},":[64],"first":[66],"benchmark":[67],"\\textbf{multi-user,":[69],"multi-turn}":[70],"travel":[71],"planning.":[72],"Built":[73],"from":[74],"user":[76],"profiles,":[77],"POI":[78],"data,":[79],"ticket":[81],"prices,":[82],"comprises":[84],"650":[85],"tasks":[86],"three":[88,120],"difficulty":[89],"levels,":[90],"each":[91],"running":[92],"synchronous":[95],"group-chat":[96],"sandbox":[97],"with":[98,152,184],"cached":[99],"tool":[100,111],"data":[101],"reproducible":[103],"offline":[104],"evaluation.":[105],"Beyond":[106],"multi-step":[108],"reasoning":[109],"use":[112],"that":[113,143,190],"already":[116],"test,":[117],"GroupTravelBench":[118],"probes":[119],"group-specific":[121],"capabilities:":[122],"\\textit{(i)":[123],"elicitation}":[124],"of":[125,133,169],"through":[128],"multi-turn":[129],"dialogue;":[130],"\\textit{(ii)":[131],"coordination}":[132],"inter-user":[134],"conflicts":[135],"via":[136],"compromise":[137],"or":[138],"subgrouping;":[139],"\\textit{(iii)":[141],"planning}":[142],"balances":[144],"We":[149],"pair":[150],"this":[151],"complementary":[154],"evaluation":[155],"framework":[156],"combining":[157],"rule-based":[158,181],"outcome":[159,182,192],"metrics":[160],"LLM-judge":[162],"process":[163],"metrics.":[164],"Across":[165],"wide":[167],"range":[168],"frontier":[170],"models,":[171],"even":[172],"strongest":[174],"agents":[175],"fall":[176],"short":[177],"on":[178],"all":[179],"four":[180],"metrics,":[183],"plan":[185],"validity":[186],"below":[187],"12\\%,":[188],"suggesting":[189],"group-level":[191],"quality":[193],"key":[196],"open":[197],"challenge":[198],"agents.":[202]},"counts_by_year":[],"updated_date":"2026-07-03T06:20:38.788640","created_date":"2026-05-28T00:00:00"}