{"id":"https://openalex.org/W7164916750","doi":"https://doi.org/10.48550/arxiv.2606.15994","title":"Agentic Framework for Deep Learning workload migration via In-Context Learning","display_name":"Agentic Framework for Deep Learning workload migration via In-Context Learning","publication_year":2026,"publication_date":"2026-06-14","ids":{"openalex":"https://openalex.org/W7164916750","doi":"https://doi.org/10.48550/arxiv.2606.15994"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.15994","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15994","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.15994","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138739587","display_name":"Qiyue Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Qiyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026894469","display_name":"Steven Ingram","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ingram, Steven","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130567211","display_name":"GEORGE VANICA","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vanica, George","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138755431","display_name":"Andi Gavrilescu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gavrilescu, Andi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138734516","display_name":"Newfel Harrat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harrat, Newfel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116471737","display_name":"Hassan Sipra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sipra, Hassan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111751370","display_name":"Sethuraman Sankaran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sankaran, Sethuraman","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10320000350475311,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10320000350475311,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.09059999883174896,"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/T12127","display_name":"Software System Performance and Reliability","score":0.08590000122785568,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/oracle","display_name":"Oracle","score":0.6450999975204468},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6378999948501587},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6183000206947327},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5698000192642212},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5284000039100647},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.3549000024795532},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.35040000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8052999973297119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6484000086784363},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6450999975204468},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6378999948501587},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6183000206947327},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5698000192642212},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5284000039100647},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3991999924182892},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.35040000081062317},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3328999876976013},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3240000009536743},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C155911762","wikidata":"https://www.wikidata.org/wiki/Q422321","display_name":"Blueprint","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.258899986743927}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.15994","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15994","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.15994","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15994","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,"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"},"sustainable_development_goals":[{"score":0.7126590013504028,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Translating":[0],"deep":[1],"learning":[2],"models":[3,203],"from":[4],"PyTorch's":[5],"flexible,":[6],"object-oriented":[7],"design":[8],"to":[9,40,86,96,116,136,177],"JAX's":[10],"functional,":[11],"stateless":[12],"setup":[13],"is":[14,23,133],"usually":[15],"a":[16,47,68,188],"manual":[17],"and":[18,33,37,75,130,150,156],"error-prone":[19],"task.":[20],"Automated":[21],"migration":[22],"challenging":[24],"because":[25],"Large":[26],"Language":[27],"Models":[28],"(LLMs)":[29],"struggle":[30],"with":[31,56,147],"strict":[32,69],"dynamic":[34,100],"API":[35],"alignment":[36],"are":[38,127],"prone":[39],"mistakes":[41],"for":[42,71,139,193],"exacting":[43],"operations.":[44],"We":[45,109],"propose":[46],"fully":[48],"autonomous":[49,113],"system":[50],"that":[51,65,143],"combines":[52],"In-Context":[53],"Learning":[54],"(ICL)":[55],"oracle-driven":[57],"self-debugging.":[58],"First,":[59],"we":[60,90],"curated":[61],"an":[62,105,112,165],"ICL":[63,145],"context":[64],"serves":[66],"as":[67],"reference":[70],"idiomatic":[72],"JAX":[73],"styling":[74],"test":[76,125],"case":[77],"generation.":[78],"Second,":[79],"instead":[80],"of":[81],"depending":[82],"on":[83,120,184],"the":[84,92,121,131,137],"LLM":[85,138],"deduce":[87],"mathematical":[88],"outputs,":[89],"run":[91],"source":[93],"PyTorch":[94],"modules":[95],"get":[97],"their":[98],"actual":[99],"tensor":[101],"states.":[102],"This":[103,160,196],"creates":[104],"unchangeable":[106],"execution":[107],"oracle.":[108],"then":[110],"use":[111],"agentic":[114,158],"loop":[115],"synthesize":[117],"tests":[118],"based":[119],"oracle":[122,148],"data.":[123],"The":[124],"cases":[126],"executed":[128],"repeatedly,":[129],"traceback":[132],"sent":[134],"back":[135],"self-correction.":[140],"Ablations":[141],"show":[142],"combining":[144],"references":[146],"grounding":[149],"self-debugging":[151],"greatly":[152],"outperforms":[153],"pure":[154],"instructional":[155],"basic":[157],"baselines.":[159],"improvement":[161],"does":[162],"not":[163],"add":[164],"excessive":[166],"computational":[167],"overhead.":[168],"Our":[169],"lightweight":[170],"pipeline":[171],"achieves":[172],"91%":[173],"numerical":[174,215],"equivalence":[175],"(compared":[176],"baseline:":[178],"9%,":[179],"instruction":[180],"+":[181],"self-debugging:":[182],"27%)":[183],"neural":[185],"modules,":[186],"providing":[187],"highly":[189],"reliable,":[190],"scalable":[191],"blueprint":[192],"cross-framework":[194],"migration.":[195],"has":[197],"been":[198],"validated":[199],"across":[200],"several":[201],"state-of-the-art":[202],"including":[204],"SAM":[205],"(segment":[206],"anything),":[207],"T5,":[208],"Code":[209],"Whisper":[210],"amongst":[211],"others":[212],"showing":[213],"high":[214],"equivalency.":[216],"Code:":[217],"https://github.com/AI-Hypercomputer/accelerator-agents/tree/main/MaxCode":[218]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-17T00:00:00"}