{"id":"https://openalex.org/W7208745765","doi":"https://doi.org/10.48550/arxiv.2609.03553","title":"GPS-Bench: A Governance Policy Benchmark for Automating Policy Analysis","display_name":"GPS-Bench: A Governance Policy Benchmark for Automating Policy Analysis","publication_year":2026,"publication_date":"2026-09-03","ids":{"openalex":"https://openalex.org/W7208745765","doi":"https://doi.org/10.48550/arxiv.2609.03553"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.03553","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03553","pdf_url":"https://arxiv.org/pdf/2609.03553","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","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/2609.03553","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5144248128","display_name":"Linh Le","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Le, Linh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132711062","display_name":"Melanie Bui","orcid":"https://orcid.org/0009-0007-4131-3790","observed_orcids":["https://orcid.org/0009-0007-4131-3790"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bui, Melanie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123952459","display_name":"My Chiffon Nguyen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, My Chiffon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149999093","display_name":"Zachary Schlosser","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schlosser, Zachary","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5120001465","display_name":"David Williams-King","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Williams-King, David","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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.6815999746322632,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.6815999746322632,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.06790000200271606,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.03480000048875809,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/policy-simulation","display_name":"policy simulation","score":0.6949999928474426},{"id":"https://openalex.org/keywords/governance-policy","display_name":"governance policy","score":0.7580000162124634},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.41499999165534973},{"id":"https://openalex.org/keywords/multi-agent-systems","display_name":"multi-agent systems","score":0.7129999995231628},{"id":"https://openalex.org/keywords/lobbying-disclosure","display_name":"lobbying disclosure","score":0.5540000200271606},{"id":"https://openalex.org/keywords/legislative-records","display_name":"legislative records","score":0.7720000147819519},{"id":"https://openalex.org/keywords/coalition-formation","display_name":"coalition formation","score":0.5509999990463257},{"id":"https://openalex.org/keywords/evidence-grounding","display_name":"evidence grounding","score":0.5049999952316284},{"id":"https://openalex.org/keywords/graph-based-methods","display_name":"graph-based methods","score":0.5960000157356262},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.8240000009536743}],"concepts":[{"id":"https://openalex.org/C123587114","wikidata":"https://www.wikidata.org/wiki/Q2101508","display_name":"Policy analysis","level":2,"score":0.5985000133514404},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5889999866485596},{"id":"https://openalex.org/C39389867","wikidata":"https://www.wikidata.org/wiki/Q380767","display_name":"Corporate governance","level":2,"score":0.5788000226020813},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4961000084877014},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.4453999996185303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43709999322891235},{"id":"https://openalex.org/C109986646","wikidata":"https://www.wikidata.org/wiki/Q546113","display_name":"Public policy","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.4163999855518341},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C83009810","wikidata":"https://www.wikidata.org/wiki/Q11204","display_name":"Legislature","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C313442","wikidata":"https://www.wikidata.org/wiki/Q778556","display_name":"Persona","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.3301999866962433},{"id":"https://openalex.org/C44725695","wikidata":"https://www.wikidata.org/wiki/Q288156","display_name":"Normative","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C100001284","wikidata":"https://www.wikidata.org/wiki/Q2248246","display_name":"Public economics","level":1,"score":0.2842999994754791},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.27639999985694885},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2639000117778778},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.03553","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03553","pdf_url":"https://arxiv.org/pdf/2609.03553","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.03553","doi":"https://doi.org/10.48550/arxiv.2609.03553","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.03553","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.03553","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.03553","pdf_url":"https://arxiv.org/pdf/2609.03553","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8999999761581421}],"sustainable_development_goals_aurora":[{"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6279119849205017}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7208745765.pdf","grobid_xml":"https://content.openalex.org/works/W7208745765.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7126406733","https://openalex.org/W4407569433","https://openalex.org/W7152378370","https://openalex.org/W7167722260","https://openalex.org/W2993471017","https://openalex.org/W7110795991","https://openalex.org/W7131180333","https://openalex.org/W7171644984","https://openalex.org/W7204448212","https://openalex.org/W7203530940"],"abstract_inverted_index":{"Policy":[0],"analysis":[1],"requires":[2,12],"more":[3],"than":[4,93],"predicting":[5],"whether":[6],"a":[7,98,106,118,155,249],"proposal":[8],"will":[9,15],"pass:":[10],"it":[11],"identifying":[13],"who":[14],"be":[16,238],"affected,":[17],"how":[18],"those":[19],"actors":[20],"respond,":[21],"and":[22,67,81,129,143,163,169,187,209,225,259,265],"what":[23,193,217,220],"follows.":[24],"LLM-based":[25],"policy":[26,57,174,268],"simulations":[27],"model":[28],"these":[29],"processes":[30],"at":[31],"scale,":[32],"but":[33],"their":[34],"validity":[35],"is":[36,43,100,196],"hard":[37],"to":[38,62],"establish":[39],"when":[40,255],"plausible":[41],"behaviour":[42],"never":[44,130],"compared":[45],"with":[46,104,213],"observed":[47],"outcomes.":[48,269],"We":[49],"introduce":[50],"GPS-Bench,":[51],"an":[52,101],"evidence-grounded":[53],"benchmark":[54],"for":[55,253],"governance":[56],"simulation":[58,152],"that":[59,235],"links":[60],"policies":[61],"relevant":[63],"actors,":[64],"actor":[65,165,257],"actions":[66],"downstream":[68],"impacts":[69],"using":[70],"legislative":[71],"records,":[72],"lobbying":[73],"disclosures,":[74],"regulatory":[75],"documents,":[76],"corporate":[77],"filings,":[78],"economic":[79],"data":[80],"other":[82],"public":[83],"evidence.":[84],"Actors":[85],"are":[86,124],"reconstructed":[87],"from":[88,121],"the":[89,110,139,145,178,182,233,241,243,263],"dated":[90],"record":[91,180,244],"rather":[92],"prompted":[94],"as":[95,126,131],"archetypes,":[96],"so":[97,232],"persona":[99],"evidence":[102,123],"object":[103],"provenance;":[105],"human-annotated":[107],"pool":[108],"forms":[109],"Gold":[111],"evaluation":[112],"set,":[113],"while":[114],"cases":[115],"labelled":[116],"by":[117],"separate":[119],"LLM":[120],"retrieved":[122],"treated":[125],"Silver":[127],"supervision":[128],"test":[132],"labels.":[133],"Because":[134],"every":[135],"inference":[136],"mode":[137],"reads":[138],"same":[140,146],"grounded":[141,179],"state":[142],"emits":[144],"schema,":[147],"GPS-Bench":[148,246],"turns":[149],"\"does":[150],"multi-agent":[151,260],"help?\"":[153],"into":[154],"controlled":[156],"comparison:":[157],"we":[158],"contrast":[159],"joint":[160,215],"reasoning,":[161],"independent":[162],"communicating":[164],"agents,":[166],"graph-based":[167],"methods":[168],"weight-level":[170],"fine-tuning":[171],"over":[172],"one":[173],"state.":[175],"Fine-tuning":[176],"on":[177],"gives":[181,248],"strongest":[183],"actor-level":[184],"impact":[185],"prediction,":[186],"decomposition":[188,194],"does":[189],"not":[190],"beat":[191],"it;":[192],"adds":[195],"mechanism.":[197],"Agents":[198],"hold":[199],"private,":[200],"non-identical":[201],"evidence,":[202,256],"each":[203],"seeing":[204],"its":[205],"own":[206],"exposure":[207],"clause,":[208],"address":[210],"named":[211],"partners":[212],"concrete":[214],"proposals,":[216],"they":[218,221],"offer,":[219],"need":[222],"in":[223],"return,":[224],"why":[226],"acting":[227,230],"together":[228],"beats":[229],"alone,":[231],"coalitions":[234],"form":[236],"can":[237],"checked":[239],"against":[240],"commitments":[242],"holds.":[245],"therefore":[247],"common":[250],"empirical":[251],"setting":[252],"studying":[254],"modelling":[258],"interaction":[261],"improve":[262],"prediction":[264],"interpretation":[266],"of":[267]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-05T00:00:00"}