{"id":"https://openalex.org/W7213675684","doi":null,"title":"PetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces","display_name":"PetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces","publication_year":2026,"publication_date":"2026-09-17","ids":{"openalex":"https://openalex.org/W7213675684"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.19883","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.19883","pdf_url":"https://arxiv.org/pdf/2609.19883","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.19883","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5144392316","display_name":"Pyrros Koussios","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Koussios, Pyrros","raw_affiliation_strings":["ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":null,"display_name":"J\u00e4ger, Benjamin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"J\u00e4ger, Benjamin","raw_affiliation_strings":["ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126654772","display_name":"John Hua Yao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yao, John Hua","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004772595","display_name":"Ajay Sridhar","orcid":"https://orcid.org/0009-0008-2268-6097","observed_orcids":["https://orcid.org/0009-0008-2268-6097"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sridhar, Ajay","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023185054","display_name":"Violet Xiang","orcid":"https://orcid.org/0000-0002-1584-6231","observed_orcids":["https://orcid.org/0000-0002-1584-6231"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang, Violet","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5152176231","display_name":"Chenhao Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Li, Chenhao","raw_affiliation_strings":["ETH Z\u00fcrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Z\u00fcrich","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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/T10028","display_name":"Topic Modeling","score":0.42800000309944153,"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":0.42800000309944153,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.12099999934434891,"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":0.0617000013589859,"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/llm-reasoning","display_name":"LLM reasoning","score":0.7839999794960022},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.7099999785423279},{"id":"https://openalex.org/keywords/petri-nets","display_name":"Petri nets","score":0.9649999737739563},{"id":"https://openalex.org/keywords/concurrent-and-distributed-systems","display_name":"concurrent and distributed systems","score":0.7900000214576721},{"id":"https://openalex.org/keywords/test-time-compute","display_name":"test-time compute","score":0.6380000114440918},{"id":"https://openalex.org/keywords/procedural-content-generation","display_name":"procedural content generation","score":0.746999979019165},{"id":"https://openalex.org/keywords/temporal-reasoning","display_name":"temporal reasoning","score":0.3190000057220459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7419999837875366},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7335000038146973},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.6313999891281128},{"id":"https://openalex.org/C182620335","wikidata":"https://www.wikidata.org/wiki/Q2852531","display_name":"Answer set programming","level":3,"score":0.5864999890327454},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5824999809265137},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.560699999332428},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.49300000071525574},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48570001125335693},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48179998993873596},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4555000066757202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43209999799728394},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3003000020980835},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28060001134872437},{"id":"https://openalex.org/C38677869","wikidata":"https://www.wikidata.org/wiki/Q724168","display_name":"Petri net","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.26930001378059387},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.26460000872612},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:arXiv.org:2609.19883","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.19883","pdf_url":"https://arxiv.org/pdf/2609.19883","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":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:2609.19883","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.19883","pdf_url":"https://arxiv.org/pdf/2609.19883","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":null,"license_id":null,"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/W7213675684.pdf","grobid_xml":"https://content.openalex.org/works/W7213675684.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416052617","https://openalex.org/W7138853489","https://openalex.org/W4416035263","https://openalex.org/W4402672103","https://openalex.org/W7140141301","https://openalex.org/W4417101652","https://openalex.org/W4415133970","https://openalex.org/W4415333929","https://openalex.org/W7161721389","https://openalex.org/W7078209886"],"abstract_inverted_index":{"Characterizing":[0],"LLM":[1,36,154],"reasoning":[2,13,37,57,121],"remains":[3],"an":[4],"open":[5],"challenge,":[6],"as":[7],"many":[8],"existing":[9],"benchmarks":[10],"isolate":[11],"specific":[12],"skills,":[14],"rely":[15],"on":[16],"external":[17],"knowledge,":[18],"or":[19],"are":[20],"costly":[21],"to":[22],"extend.":[23],"We":[24],"introduce":[25],"PetriBench,":[26],"a":[27,45,86,140],"compact,":[28],"fully":[29],"self-contained,":[30],"and":[31,52,65,71,79,91,123,142,150],"scalable":[32],"benchmark":[33],"for":[34,48,145],"evaluating":[35],"over":[38],"dynamic":[39],"state":[40],"spaces":[41],"using":[42],"Petri":[43],"nets,":[44],"mature":[46],"formalism":[47],"modeling":[49],"real-world":[50],"concurrent":[51],"distributed":[53],"systems.":[54],"PetriBench":[55,138],"organizes":[56],"into":[58],"four":[59],"task":[60],"families":[61],"varying":[62],"by":[63,75],"scope":[64],"temporal":[66],"horizon,":[67],"with":[68,97,119,130],"Easy,":[69],"Medium,":[70],"Hard":[72],"levels":[73],"generated":[74],"increasing":[76],"structural":[77,131],"complexity":[78],"evaluated":[80],"against":[81],"exact":[82],"ground":[83],"truth.":[84],"Across":[85],"diverse":[87],"set":[88],"of":[89,153],"proprietary":[90],"open-weight":[92],"models,":[93],"accuracy":[94],"decreases":[95],"consistently":[96],"difficulty,":[98],"while":[99],"harder":[100],"instances":[101],"expose":[102],"increasingly":[103],"distinct":[104],"task-specific":[105],"capability":[106],"profiles.":[107],"Additional":[108],"analyses":[109],"show":[110,136],"that":[111,124,137],"test-time":[112],"compute":[113],"improves":[114],"performance":[115],"but":[116],"interacts":[117],"differently":[118],"different":[120],"tasks,":[122],"procedural":[125],"generation":[126],"yields":[127],"smooth":[128],"scaling":[129,151],"complexity.":[132],"Together,":[133],"these":[134],"results":[135],"provides":[139],"unified":[141],"extensible":[143],"setting":[144],"probing":[146],"the":[147],"strengths,":[148],"limits,":[149],"behavior":[152],"reasoning.":[155]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-20T00:00:00"}