{"id":"https://openalex.org/W7225245213","doi":"https://doi.org/10.48550/arxiv.2611.04228","title":"DualWorldBench: Can Agents Plan Deliveries across Symbolic and Grounded Worlds?","display_name":"DualWorldBench: Can Agents Plan Deliveries across Symbolic and Grounded Worlds?","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225245213","doi":"https://doi.org/10.48550/arxiv.2611.04228"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.04228","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.04228","pdf_url":"https://arxiv.org/pdf/2611.04228","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.04228","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160640872","display_name":"Yang Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Yang","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University","School of Intelligence Science and Technology , Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Intelligence Science and Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160713765","display_name":"Bin Wen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen, Bin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053702080","display_name":"Danyang Peng","orcid":"https://orcid.org/0000-0002-0425-9760","observed_orcids":["https://orcid.org/0000-0002-0425-9760"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng, Danyang","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University","School of Intelligence Science and Technology , Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Intelligence Science and Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153402989","display_name":"Hong-Jie You","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"You, Hong-Jie","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University","School of Artificial Intelligence , Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Artificial Intelligence , Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160679615","display_name":"Zi-Qiao Shang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shang, Zi-Qiao","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University","School of Intelligence Science and Technology , Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Intelligence Science and Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160691396","display_name":"Lan-Zhe Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo, Lan-Zhe","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University","School of Intelligence Science and Technology , Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Intelligence Science and Technology , Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.8604000210762024,"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":0.8604000210762024,"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":0.0714000016450882,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0272000003606081,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/multimodal-agents","display_name":"multimodal agents","score":0.753000020980835},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.45899999141693115},{"id":"https://openalex.org/keywords/symbolic-planning","display_name":"symbolic planning","score":0.9330000281333923},{"id":"https://openalex.org/keywords/time-constraints","display_name":"time constraints","score":0.7829999923706055},{"id":"https://openalex.org/keywords/topological-complexity","display_name":"topological complexity","score":0.7210000157356262},{"id":"https://openalex.org/keywords/vision-language-agents","display_name":"vision-language agents","score":0.527999997138977},{"id":"https://openalex.org/keywords/scene-understanding","display_name":"scene understanding","score":0.41499999165534973}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6183000206947327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.614799976348877},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5329999923706055},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5102999806404114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4812999963760376},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.4666000008583069},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.4431000053882599},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4388999938964844},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.4350999891757965},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.40860000252723694},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3855000138282776},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3151000142097473},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2964000105857849},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.26989999413490295},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.2696000039577484},{"id":"https://openalex.org/C2780210234","wikidata":"https://www.wikidata.org/wiki/Q422638","display_name":"Action plan","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26570001244544983},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.04228","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.04228","pdf_url":"https://arxiv.org/pdf/2611.04228","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.2611.04228","doi":"https://doi.org/10.48550/arxiv.2611.04228","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04228","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:2611.04228","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.04228","pdf_url":"https://arxiv.org/pdf/2611.04228","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":[{"id":"https://openalex.org/G6712651544","display_name":null,"funder_award_id":"B26023","funder_id":"https://openalex.org/F4320336698","funder_display_name":"Overseas Expertise Introduction Center for Discipline Innovation of Food Nutrition and Human Health (111 Center)"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336698","display_name":"Overseas Expertise Introduction Center for Discipline Innovation of Food Nutrition and Human Health (111 Center)","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225245213.pdf","grobid_xml":"https://content.openalex.org/works/W7225245213.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W4385327683","https://openalex.org/W4385682136","https://openalex.org/W4391591592","https://openalex.org/W4391833363","https://openalex.org/W4400104385","https://openalex.org/W4400373871","https://openalex.org/W4405626567","https://openalex.org/W4415278944","https://openalex.org/W4416257309","https://openalex.org/W4417536287","https://openalex.org/W6891885324","https://openalex.org/W7117131166","https://openalex.org/W7128436557","https://openalex.org/W7131209732","https://openalex.org/W7150908814","https://openalex.org/W7160324695","https://openalex.org/W7202188380","https://openalex.org/W7213293145","https://openalex.org/W7214708256"],"related_works":["https://openalex.org/W7128489030","https://openalex.org/W4403754279","https://openalex.org/W7162637836","https://openalex.org/W4405095661","https://openalex.org/W4401024187","https://openalex.org/W7163677629","https://openalex.org/W7203681643","https://openalex.org/W7221052321","https://openalex.org/W7118417445","https://openalex.org/W4417287200"],"abstract_inverted_index":{"Recent":[0],"multimodal":[1,44,100],"agents":[2,30,127,194],"have":[3],"shown":[4],"promising":[5],"progress":[6],"in":[7,138],"embodied":[8],"planning":[9,39,55,78,91],"and":[10,35,43,59,83,102,111,121,155,181,201],"web":[11],"interaction.":[12],"However,":[13],"existing":[14],"evaluations":[15],"often":[16],"rely":[17],"on":[18],"simplified":[19],"tasks":[20],"with":[21,96,195],"limited":[22],"combinatorial":[23],"structure,":[24],"leaving":[25],"it":[26],"unclear":[27],"whether":[28],"current":[29],"can":[31],"robustly":[32],"integrate":[33],"perception":[34,154],"reasoning":[36],"for":[37,52,193],"multi-goal":[38,183],"under":[40,56,79,92,134],"temporal,":[41],"physical,":[42],"constraints.":[45],"We":[46],"introduce":[47],"DualWorldBench,":[48],"a":[49,64,104,115,190],"unified":[50],"benchmark":[51],"evaluating":[53],"agent":[54],"controlled":[57,93],"symbolic--temporal":[58],"grounded--topological":[60],"complexity.":[61],"Built":[62],"around":[63],"shared":[65],"pickup--delivery":[66],"interface,":[67],"DualWorldBench":[68,188],"consists":[69],"of":[70],"three":[71],"complementary":[72],"components:":[73],"TextWorld,":[74,126],"which":[75,87],"isolates":[76],"symbolic":[77,174],"varying":[80],"task":[81,132],"compositions":[82],"release":[84],"dynamics;":[85],"SimWorld,":[86,139],"evaluates":[88],"grounded":[89,140,176],"path":[90],"topological":[94],"variation":[95],"text,":[97],"image,":[98],"or":[99,175],"inputs;":[101],"DualWorld-VQA,":[103],"diagnostic":[105],"suite":[106],"spanning":[107],"perception,":[108],"scene":[109],"understanding,":[110],"planning.":[112,124,164],"Experiments":[113],"reveal":[114],"common":[116],"gap":[117],"between":[118],"local":[119],"understanding":[120,157],"globally":[122,179],"consistent":[123],"In":[125],"struggle":[128],"to":[129],"derive":[130],"optimal":[131],"sequences":[133],"interacting":[135],"temporal":[136],"constraints;":[137],"observations":[141],"are":[142,203],"not":[143,159],"reliably":[144],"converted":[145],"into":[146,162,178],"feasible":[147,180],"action":[148],"sequences.":[149],"DualWorld-VQA":[150],"further":[151],"confirms":[152],"that":[153],"topology":[156],"do":[158],"necessarily":[160],"translate":[161],"constrained":[163],"Together,":[165],"these":[166],"results":[167],"identify":[168],"the":[169],"central":[170],"challenge":[171],"as":[172,189],"composing":[173],"evidence":[177],"efficient":[182],"plans.":[184],"These":[185],"findings":[186],"establish":[187],"challenging":[191],"testbed":[192],"tighter":[196],"perception--reasoning--planning":[197],"integration.":[198],"All":[199],"datasets":[200],"code":[202],"publicly":[204],"available":[205],"at":[206],"our":[207],"project":[208],"website":[209],"https://dualworld.netlify.app/.":[210]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-05T00:00:00"}
