{"id":"https://openalex.org/W7225731350","doi":"https://doi.org/10.5281/zenodo.24118728","title":"How Much Is an Agent's History Worth? A Law of Evaluation Transfer Across Agent Versions, Tested in Pre-Registered Studies","display_name":"How Much Is an Agent's History Worth? A Law of Evaluation Transfer Across Agent Versions, Tested in Pre-Registered Studies","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225731350","doi":"https://doi.org/10.5281/zenodo.24118728"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.24118728","doi":"https://doi.org/10.5281/zenodo.24118728","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24118728","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"article-journal"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.24118728","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161389235","display_name":"Rayen Zargui","orcid":"https://orcid.org/0009-0008-8250-9180","observed_orcids":["https://orcid.org/0009-0008-8250-9180"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zargui, Rayen","raw_affiliation_strings":["Independent researcher"],"raw_orcid":"https://orcid.org/0009-0008-8250-9180","affiliations":[{"raw_affiliation_string":"Independent researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5161389235"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T13904","display_name":"Artificial Intelligence Applications","score":0.13420000672340393,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.13420000672340393,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.10429999977350235,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.06920000165700912,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.585099995136261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5037999749183655},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.49390000104904175},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.47769999504089355},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3682999908924103},{"id":"https://openalex.org/C185767445","wikidata":"https://www.wikidata.org/wiki/Q207952","display_name":"Law of large numbers","level":3,"score":0.32760000228881836},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29350000619888306},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28209999203681946},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2797999978065491},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.27720001339912415},{"id":"https://openalex.org/C47458327","wikidata":"https://www.wikidata.org/wiki/Q910404","display_name":"Random graph","level":3,"score":0.26969999074935913}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.24118728","doi":"https://doi.org/10.5281/zenodo.24118728","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24118728","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"article-journal"},{"id":"doi:10.5281/zenodo.24118729","doi":"https://doi.org/10.5281/zenodo.24118729","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24118729","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"article-journal"}],"best_oa_location":{"id":"doi:10.5281/zenodo.24118728","doi":"https://doi.org/10.5281/zenodo.24118728","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.24118728","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"article-journal"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Each":[0],"new":[1,70],"version":[2,139],"of":[3,28,68,185,210,238,249],"an":[4,258],"AI":[5],"agent":[6,31],"is":[7,42,54,65],"evaluated":[8],"from":[9,141,159,290],"scratch,":[10],"although":[11],"earlier":[12,87],"agents\u2019":[13],"outcomes":[14],"on":[15,215,262],"the":[16,52,66,69,74,79,83,95,98,108,122,126,130,145,149,163,181,186,189,207,211,216,224,242,263],"same":[17,109,217,264],"tasks":[18,40,50,110,162,182,194,218],"are":[19,30,305],"known.":[20],"We":[21,89],"organise":[22],"this":[23],"history":[24],"as":[25,55,57],"a":[26,93,100,119,174,255,279,287],"graph":[27,53,75,96,146],"agents\u2014nodes":[29],"versions":[32,225],"with":[33,51,78,82,104,156,188],"their":[34],"task-level":[35,72],"outcomes\u2014and":[36],"ask":[37],"how":[38],"many":[39],"it":[41,91],"worth.":[43],"A":[44],"closed-form":[45],"law":[46],"answers:":[47],"testing":[48,58,246],"m":[49],"precise":[56],"m/(1\u2212\u03c12":[59],")":[60],"at":[61,228,278],"random,":[62],"where":[63],"\u03c1\u00b2":[64],"share":[67],"version\u2019s":[71],"variance":[73],"explains":[76],"(\u03c6\u00b2":[77],"predecessor,":[80],"\u03b7\u00b2":[81],"difficulty":[84],"seen":[85],"by":[86,118,178,227,284],"agents).":[88],"turn":[90],"into":[92],"method:":[94],"chooses":[97],"tasks,":[99,265],"cross-fitted":[101,190],"estimator":[102],"estimates":[103,282],"calibrated":[105],"intervals,":[106],"and":[107,144,203,275],"decide":[111],"keep-or-replace.":[112],"In":[113],"eight":[114],"studies,":[115],"each":[116],"pre-registered":[117,298],"git":[120],"tag,":[121],"predecessor":[123],"law,":[124,147],"given":[125,148],"true":[127,150],"\u03c6\u00b2,":[128],"matched":[129],"observed":[131],"gain":[132],"within":[133,152],"3.9%":[134],"(median)":[135],"over":[136,154,167],"219":[137],"real":[138],"transitions":[140],"five":[142],"benchmarks,":[143],"\u03b7\u00b2,":[151],"7.7%":[153],"90;":[155],"\u03c6\u00b2":[157],"estimated":[158],"20":[160,192],"tested":[161],"median":[164],"per-transition":[165],"error,":[166],"simulated":[168],"draws,":[169],"was":[170],"5.3%":[171],"(exploratory),":[172],"but":[173],"single":[175],"evaluation":[176,268,276],"erred":[177,219],"20%.":[179],"Choosing":[180],"gives":[183],"most":[184],"gain:":[187],"estimator,":[191],"graph-chosen":[193],"were":[195,301],"worth":[196],"32\u201344":[197],"random":[198,245],"ones":[199],"in":[200,247],"two":[201],"confirmations":[202],"90%":[204],"intervals":[205],"covered":[206],"truth":[208],"0.944\u20130.959":[209],"time;":[212],"decisions":[213],"taken":[214],"32\u201354%":[220],"less":[221],"often":[222],"when":[223],"differ":[226],"least":[229],"5":[230],"points.":[231],"On":[232],"13":[233],"newer":[234],"AppWorld":[235],"agents,":[236],"four":[237],"them":[239],"multi-agent":[240],"systems,":[241],"method":[243],"beat":[244],"24":[248],"26":[250],"evaluations":[251],"(\u00d71.31).":[252],"Agents":[253],"sharing":[254],"scaffold":[256],"or":[257],"agentic":[259],"pattern":[260],"fail":[261],"without":[266],"making":[267],"more":[269],"efficient.":[270],"When":[271],"results":[272],"arrive":[273],"asynchronously":[274],"stops":[277],"deadline,":[280],"naive":[281],"overshoot":[283],"6.3":[285],"points;":[286],"correction":[288],"learned":[289],"older":[291],"agents":[292],"did":[293],"not":[294],"transfer.":[295],"Of":[296],"43":[297],"hypotheses,":[299],"35":[300],"supported;":[302],"all":[303],"failures":[304],"reported.":[306]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-11T00:00:00"}