{"id":"https://openalex.org/W7133318530","doi":"https://doi.org/10.48550/arxiv.2603.01712","title":"FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language Agents","display_name":"FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language Agents","publication_year":2026,"publication_date":"2026-03-02","ids":{"openalex":"https://openalex.org/W7133318530","doi":"https://doi.org/10.48550/arxiv.2603.01712"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.01712","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01712","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.01712","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128014579","display_name":"Qizheng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li, Qizheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127936964","display_name":"Yifei Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yifei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127915655","display_name":"Xiao Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128019762","display_name":"Xu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127979347","display_name":"Zhuo Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhuo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128021160","display_name":"Weiqing Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Weiqing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127948903","display_name":"Jiang Bian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bian, Jiang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5128014579"],"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/T10028","display_name":"Topic Modeling","score":0.44620001316070557,"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":0.44620001316070557,"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":0.10080000013113022,"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/T13629","display_name":"Text Readability and Simplification","score":0.0608999989926815,"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/domain","display_name":"Domain (mathematical analysis)","score":0.5117999911308289},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.5009999871253967},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.46860000491142273},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.40950000286102295},{"id":"https://openalex.org/keywords/data-driven","display_name":"Data-driven","score":0.40369999408721924},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.38350000977516174},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.32359999418258667},{"id":"https://openalex.org/keywords/unexpected-events","display_name":"Unexpected events","score":0.3091000020503998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7450000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5126000046730042},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5117999911308289},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.5009999871253967},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.40950000286102295},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4083999991416931},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40540000796318054},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.40369999408721924},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C9628104","wikidata":"https://www.wikidata.org/wiki/Q788009","display_name":"Autonomous system (mathematics)","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2531000077724457},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.01712","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01712","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.01712","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01712","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":"article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.7114436626434326,"id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fine-tuning":[0],"large":[1],"language":[2],"models":[3],"for":[4],"vertical":[5],"domains":[6],"remains":[7],"a":[8,54,77],"labor-intensive":[9],"and":[10,21,80,136,185,214],"expensive":[11],"process,":[12],"requiring":[13],"domain":[14],"experts":[15,127],"to":[16,132,175],"curate":[17],"data,":[18],"configure":[19],"training,":[20],"iteratively":[22,81,133],"diagnose":[23,134],"model":[24],"behavior.":[25],"Despite":[26],"growing":[27,91],"interest":[28],"in":[29,89,208],"autonomous":[30,122,218],"machine":[31],"learning,":[32],"no":[33],"prior":[34],"work":[35],"has":[36],"tackled":[37],"end-to-end":[38],"LLM":[39,219],"fine-tuning":[40,138,146],"with":[41,73,152,178],"agents.":[42],"Can":[43],"LLM-based":[44],"agents":[45,58,147,192],"automate":[46],"this":[47,52,103],"complete":[48],"process?":[49],"We":[50,117],"frame":[51],"as":[53],"substantially":[55],"open":[56],"problem:":[57],"must":[59],"navigate":[60],"an":[61,108,121],"open-ended":[62],"search":[63],"space":[64],"spanning":[65],"data":[66,70,182],"curation":[67],"from":[68,195,200],"diverse":[69],"sources,":[71],"processing":[72],"complex":[74],"tools,":[75],"building":[76],"training":[78],"pipeline,":[79],"refining":[82],"their":[83],"approach":[84,172],"based":[85],"on":[86,141,158,181],"evaluation":[87],"outcomes":[88],"rapidly":[90],"logs--an":[92],"overall":[93],"scenario":[94],"far":[95],"more":[96],"intricate":[97],"than":[98],"existing":[99],"benchmarks.":[100],"To":[101],"study":[102],"question,":[104],"we":[105],"introduce":[106],"FT-Dojo,":[107],"interactive":[109],"environment":[110],"comprising":[111],"13":[112,162],"tasks":[113,163],"across":[114,164],"5":[115],"domains.":[116,167],"further":[118],"develop":[119],"FT-Agent,":[120],"system":[123],"that":[124,144,170,191],"mirrors":[125],"human":[126],"by":[128],"leveraging":[129],"evaluation-driven":[130],"feedback":[131],"failures":[135,196],"refine":[137],"strategies.":[139],"Experiments":[140],"FT-Dojo":[142],"demonstrate":[143],"purpose-built":[145],"significantly":[148],"outperform":[149],"general-purpose":[150],"alternatives,":[151],"FT-Agent":[153],"achieving":[154],"the":[155,171,212],"best":[156],"performance":[157],"10":[159],"out":[160],"of":[161,217],"all":[165],"five":[166],"Ablations":[168],"show":[169],"generalizes":[173],"effectively":[174],"3B":[176],"models,":[177],"additional":[179],"insights":[180],"scaling":[183],"trade-offs":[184],"backbone":[186],"sensitivity.":[187],"Case":[188],"analyses":[189],"reveal":[190],"can":[193],"recover":[194],"through":[197],"cumulative":[198],"learning":[199],"historical":[201],"experience,":[202],"while":[203],"also":[204],"exposing":[205],"fundamental":[206],"limitations":[207],"causal":[209],"reasoning--highlighting":[210],"both":[211],"promise":[213],"current":[215],"boundaries":[216],"fine-tuning.":[220]},"counts_by_year":[],"updated_date":"2026-03-04T07:09:34.246503","created_date":"2026-03-04T00:00:00"}