{"id":"https://openalex.org/W7165680030","doi":"https://doi.org/10.48550/arxiv.2606.22813","title":"Active Inference as the Test-Time Scaling Law for Physical AI Agents","display_name":"Active Inference as the Test-Time Scaling Law for Physical AI Agents","publication_year":2026,"publication_date":"2026-06-22","ids":{"openalex":"https://openalex.org/W7165680030","doi":"https://doi.org/10.48550/arxiv.2606.22813"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.22813","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22813","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.22813","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072240167","display_name":"Omar Hashash","orcid":"https://orcid.org/0000-0003-0086-5250"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hashash, Omar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139190417","display_name":"Christo Kurisummoottil Thomas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas, Christo Kurisummoottil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139141323","display_name":"Walid Saad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saad, Walid","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139186939","display_name":"Merouane Debbah","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Debbah, Merouane","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139175585","display_name":"Karl Friston","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Friston, Karl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5045981641","display_name":"Adeel Razi","orcid":"https://orcid.org/0000-0002-0779-9439"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Razi, Adeel","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":false,"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/T11883","display_name":"Embodied and Extended Cognition","score":0.7336999773979187,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11883","display_name":"Embodied and Extended Cognition","score":0.7336999773979187,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.025100000202655792,"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/T10982","display_name":"Motor Control and Adaptation","score":0.023399999365210533,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6814000010490417},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6025000214576721},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4629000127315521},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4442000091075897},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4404999911785126},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4221000075340271},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.40560001134872437}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6814000010490417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6046000123023987},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6025000214576721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5794000029563904},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4629000127315521},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4442000091075897},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4221000075340271},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42010000348091125},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.40560001134872437},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.3160000145435333},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.2946000099182129},{"id":"https://openalex.org/C2988430800","wikidata":"https://www.wikidata.org/wiki/Q428971","display_name":"Scaling law","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.22813","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22813","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.22813","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22813","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,74,105,113,177],"paper,":[2],"a":[3,124,149,156,181,235],"novel":[4],"test-time":[5],"scaling":[6,17,39,102,161,216],"law":[7,18,40,103],"for":[8],"physical":[9,20,236],"artificial":[10],"intelligence":[11],"(AI)":[12],"agents":[13,22,52],"is":[14,41,121,189],"introduced.":[15],"This":[16,118,191],"enables":[19],"AI":[21,237],"to":[23,29,57,79,194,262],"reason":[24],"with":[25,53,112,229],"their":[26,65],"world":[27,212],"models":[28],"generalize":[30],"in":[31,43,59,97,129,207],"unforeseen":[32,89,263],"scenarios":[33,264],"at":[34,115,172,204],"test":[35,116,173,205],"time.":[36,117,174],"The":[37,100,151],"derived":[38,226],"grounded":[42],"the":[44,54,60,77,86,109,133,138,160,165,209,225,230,248],"first":[45],"principle":[46],"of":[47,234],"active":[48],"inference,":[49],"which":[50,64,130],"equips":[51],"general":[55],"objective":[56],"survive":[58],"real":[61],"world,":[62],"under":[63,145],"specific":[66],"task":[67,245],"objectives":[68],"are":[69,135],"subsumed.":[70],"Active":[71],"inference":[72,127,183,267],"achieves":[73],"by":[75,106,199,219,269],"providing":[76],"reasoning":[78,114,139],"resolve":[80],"prediction":[81,143],"errors":[82,144],"that":[83,140,163,247],"arise":[84],"when":[85],"agent":[87],"encounters":[88],"situations":[90],"outside":[91],"its":[92],"training":[93,198,223],"distribution,":[94],"enabling":[95],"generalization":[96,261],"non-stationary":[98],"environments.":[99],"proposed":[101,249],"captures":[104],"dynamically":[107],"updating":[108],"agent's":[110],"policy":[111,119,134,154,210],"update":[120],"modeled":[122],"as":[123,148],"soft":[125],"Bayesian":[126,256],"process":[128],"beliefs":[131],"about":[132],"updated":[136],"using":[137],"reduces":[141],"expected":[142],"allowable":[146],"policies":[147],"likelihood.":[150],"resulting":[152],"posterior":[153],"admits":[155],"biological":[157],"interpretation,":[158],"recovering":[159],"mechanism":[162],"engages":[164],"brain's":[166],"basal":[167],"ganglia":[168],"and":[169,211,222,254],"prefrontal":[170],"cortex":[171],"To":[175],"solve":[176],"analytically":[178],"intractable":[179],"problem,":[180],"variational":[182],"solution":[184,192,227,250],"minimizing":[185],"free":[186],"energy":[187],"bounds":[188],"developed.":[190],"extends":[193],"enable":[195],"learning":[196],"beyond":[197],"reinforcing":[200],"new":[201],"instances,":[202],"resolved":[203],"time,":[206],"both":[208],"model.":[213],"Unlike":[214],"existing":[215],"laws":[217],"constrained":[218],"model":[220],"size":[221],"data,":[224],"scales":[228],"continuous":[231],"real-world":[232],"experience":[233],"agent.":[238],"Simulation":[239],"results":[240],"on":[241],"an":[242],"autonomous":[243],"driving":[244],"demonstrate":[246],"outperforms":[251],"model-free":[252],"Q-learning":[253],"model-based":[255],"reinforcement":[257],"learning,":[258],"achieving":[259],"robust":[260],"while":[265],"improving":[266],"efficiency":[268],"over":[270],"36%.":[271]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-24T00:00:00"}