{"id":"https://openalex.org/W7202257420","doi":"https://doi.org/10.5281/zenodo.21907348","title":"The Little Scientist: LLM Agent-Driven Discovery via the Scientific Method","display_name":"The Little Scientist: LLM Agent-Driven Discovery via the Scientific Method","publication_year":2026,"publication_date":"2026-08-12","ids":{"openalex":"https://openalex.org/W7202257420","doi":"https://doi.org/10.5281/zenodo.21907348"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.16951","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.16951","pdf_url":"https://arxiv.org/pdf/2608.16951","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/2608.16951","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159969339","display_name":"Travis Smith","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Smith, Travis","raw_affiliation_strings":["Independent Researcher , S\u00e3o Miguel , Azores , Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher , S\u00e3o Miguel , Azores , Portugal","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5159969339"],"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/T13904","display_name":"Artificial Intelligence Applications","score":0.32690000534057617,"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":0.32690000534057617,"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":0.14949999749660492,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.14069999754428864,"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-based-agents","display_name":"LLM agents","score":0.8500000238418579},{"id":"https://openalex.org/keywords/automated-algorithm-design","display_name":"automated algorithm design","score":0.8610000014305115},{"id":"https://openalex.org/keywords/scientific-method","display_name":"scientific method","score":0.9229999780654907},{"id":"https://openalex.org/keywords/hypothesis-generation","display_name":"hypothesis generation","score":0.6370000243186951},{"id":"https://openalex.org/keywords/dna-motif-discovery","display_name":"DNA motif discovery","score":0.890999972820282},{"id":"https://openalex.org/keywords/transcription-factor-binding-sites","display_name":"transcription factor binding sites","score":0.6460000276565552},{"id":"https://openalex.org/keywords/ablation-study","display_name":"ablation study","score":0.6359999775886536},{"id":"https://openalex.org/keywords/token-efficiency","display_name":"token efficiency","score":0.4659999907016754}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6154000163078308},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.557699978351593},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.4341999888420105},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37380000948905945},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C2780990831","wikidata":"https://www.wikidata.org/wiki/Q319141","display_name":"Conjecture","level":2,"score":0.36230000853538513},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3587999939918518},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34060001373291016},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C138379479","wikidata":"https://www.wikidata.org/wiki/Q1116876","display_name":"Scientific modelling","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.272599995136261},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26179999113082886},{"id":"https://openalex.org/C3017489831","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Running time","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C195732255","wikidata":"https://www.wikidata.org/wiki/Q981008","display_name":"Sociology of scientific knowledge","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:arXiv.org:2608.16951","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.16951","pdf_url":"https://arxiv.org/pdf/2608.16951","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.2608.16951","doi":"https://doi.org/10.48550/arxiv.2608.16951","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.16951","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"},{"id":"doi:10.5281/zenodo.21907348","doi":"https://doi.org/10.5281/zenodo.21907348","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21907348","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":"Preprint"},{"id":"doi:10.5281/zenodo.21907349","doi":"https://doi.org/10.5281/zenodo.21907349","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21907349","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":"Preprint"},{"id":"doi:10.5281/zenodo.23930337","doi":"https://doi.org/10.5281/zenodo.23930337","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23930337","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.16951","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.16951","pdf_url":"https://arxiv.org/pdf/2608.16951","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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7202257420.pdf","grobid_xml":"https://content.openalex.org/works/W7202257420.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W4415108068","https://openalex.org/W7083291402","https://openalex.org/W7127370547","https://openalex.org/W7162766506","https://openalex.org/W7202198080"],"related_works":["https://openalex.org/W7148462264","https://openalex.org/W7220696367","https://openalex.org/W4415335512","https://openalex.org/W7136918992","https://openalex.org/W4403324055","https://openalex.org/W4416191637","https://openalex.org/W7127605006","https://openalex.org/W7134804927","https://openalex.org/W7125923324","https://openalex.org/W7131392445"],"abstract_inverted_index":{"Scientific":[0],"discovery":[1],"emerges":[2],"from":[3,100,174,231],"cycles":[4],"of":[5,25,37,143,149,163],"hypothesis,":[6,68],"implementation,":[7],"empirical":[8],"testing,":[9],"and":[10,72,82,131,178,192,205,218,227,263,277,283],"feedback.":[11],"Can":[12],"this":[13,128,258],"process":[14,39,96],"be":[15],"automated?":[16],"We":[17,45,124],"approach":[18],"automated":[19],"algorithm":[20,99,230],"design":[21],"through":[22,34],"the":[23,26,38,54,95,112,135,144,160,175,180,189,214,219,228,232,254,267,269],"lens":[24],"scientific":[27,55,137],"method,":[28],"where":[29],"an":[30,41,58,75,98],"LLM-based":[31],"agent":[32,60,66,85],"goes":[33],"each":[35],"step":[36],"in":[40,61,253],"iterative":[42],"fashion.":[43],"Results:":[44],"present":[46],"The":[47,157,237],"Little":[48],"Scientist,":[49],"a":[50,62,64,83,139,170,193,210],"framework":[51,198],"that":[52,78,103,132,241],"maps":[53],"method":[56,129],"onto":[57],"LLM":[59,242],"loop:":[63],"Scientist":[65],"iterates":[67],"prediction,":[69],"code,":[70],"test,":[71],"reconciliation":[73],"inside":[74],"evaluation":[76],"environment":[77],"returns":[79],"structured":[80],"diagnostics,":[81],"Kuhn":[84],"injects":[86],"paradigm-shifting":[87],"reframings":[88],"at":[89,187,199],"plateaus.":[90],"On":[91,209],"DNA":[92],"motif":[93],"discovery,":[94],"wrote":[97],"scratch":[101],"(DALE)":[102],"outperforms":[104],"STREME":[105],"across":[106],"132":[107],"ENCODE":[108],"transcription":[109],"factors":[110],"on":[111,202,257],"shuffled-negative":[113],"benchmark":[114],"(mean":[115],"AUROC":[116],"0.842":[117],"vs.":[118],"0.803)":[119],"while":[120],"running":[121],"11x":[122],"faster.":[123],"then":[125],"asked":[126],"why":[127,284],"worked,":[130],"question":[133],"became":[134],"paper's":[136],"core:":[138],"preregistered,":[140],"controlled":[141],"teardown":[142],"framework's":[145],"own":[146],"scaffolding":[147],"consisting":[148],"ten":[150,164],"ablation":[151],"arms":[152,166],"against":[153],"one-shot":[154],"bandit":[155,171,221],"nulls.":[156],"answer":[158],"overturned":[159],"premise.":[161],"Seven":[162],"loop":[165,216],"fail":[167],"to":[168,224],"beat":[169],"drawing":[172],"samples":[173],"same":[176],"model":[177],"prompt,":[179],"full":[181],"scaffold":[182],"performs":[183],"below":[184],"blind":[185],"sampling":[186],"7-8x":[188],"token":[190],"cost,":[191],"floor-prompt":[194],"arm":[195],"with":[196],"no":[197],"all":[200],"wins":[201],"both":[203],"score":[204],"value":[206],"per":[207],"token.":[208],"held-out":[211],"genomic":[212],"benchmark,":[213],"best":[215,220],"artifact":[217],"draw":[222],"agree":[223],"within":[225],"0.002,":[226],"DALE":[229],"initial":[233],"experiment":[234],"scored":[235],"similarly.":[236],"convergent":[238],"picture":[239],"is":[240,260,266],"agents":[243],"do":[244],"not":[245],"reason":[246],"their":[247],"way":[248],"past":[249],"what":[250],"training":[251],"placed":[252],"weights.":[255],"Autoresearch,":[256],"evidence,":[259],"sampling,":[261],"selection,":[262],"remixing,":[264],"which":[265],"bet":[268],"Evolve-family":[270],"architectures":[271],"made":[272],"when":[273],"they":[274],"chose":[275],"populations":[276],"external":[278],"selection":[279],"over":[280],"scratchpad":[281],"reasoning,":[282],"those":[285],"choices":[286],"were":[287],"right.":[288]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-08-13T00:00:00"}