{"id":"https://openalex.org/W7225832018","doi":"https://doi.org/10.48550/arxiv.2611.13452","title":"SLIC: Reinforcement Fine-Tuning Small LMs for Multi-Turn Analog Circuit Optimization","display_name":"SLIC: Reinforcement Fine-Tuning Small LMs for Multi-Turn Analog Circuit Optimization","publication_year":2026,"publication_date":"2026-11-10","ids":{"openalex":"https://openalex.org/W7225832018","doi":"https://doi.org/10.48550/arxiv.2611.13452"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2611.13452","doi":"https://doi.org/10.48550/arxiv.2611.13452","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.13452","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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2611.13452","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161437768","display_name":"Yan Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021178333","display_name":"Zhengqi Gao","orcid":"https://orcid.org/0000-0002-1515-4198","observed_orcids":["https://orcid.org/0000-0002-1515-4198"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Zhengqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030063621","display_name":"Ching-Yun Ko","orcid":"https://orcid.org/0000-0002-8966-8570","observed_orcids":["https://orcid.org/0000-0002-8966-8570"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ko, Ching-Yun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161437931","display_name":"Zhang-Wei Hong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Zhang-Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161475890","display_name":"Wenjie Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Wenjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161467499","display_name":"Tao Yu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161468187","display_name":"Xin Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066048721","display_name":"Duane S. Boning","orcid":"https://orcid.org/0000-0002-0417-445X","observed_orcids":["https://orcid.org/0000-0002-0417-445X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boning, Duane S.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5081981092","display_name":"Ruonan Han","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Ruonan","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/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.5317000150680542,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.5317000150680542,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10323","display_name":"Analog and Mixed-Signal Circuit Design","score":0.19099999964237213,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.041200000792741776,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7434999942779541},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5347999930381775},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.5267000198364258},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5077999830245972},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5030999779701233},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4546999931335449},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44940000772476196},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.39320001006126404},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.37869998812675476},{"id":"https://openalex.org/C190560348","wikidata":"https://www.wikidata.org/wiki/Q3245116","display_name":"Circuit design","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.36890000104904175},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.34369999170303345},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C46362747","wikidata":"https://www.wikidata.org/wiki/Q173431","display_name":"CMOS","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.3142000138759613},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C2777767291","wikidata":"https://www.wikidata.org/wiki/Q1080291","display_name":"Sizing","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C530198007","wikidata":"https://www.wikidata.org/wiki/Q80831","display_name":"Integrated circuit","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.296999990940094},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.27720001339912415},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C34972735","wikidata":"https://www.wikidata.org/wiki/Q2920267","display_name":"Engineering design process","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2611.13452","doi":"https://doi.org/10.48550/arxiv.2611.13452","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.13452","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"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2611.13452","doi":"https://doi.org/10.48550/arxiv.2611.13452","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.13452","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Analog":[0],"integrated":[1],"circuit":[2,61,66],"(IC)":[3],"design":[4,22,36],"is":[5],"a":[6,46,52,185,226],"multi-turn,":[7],"simulator-grounded":[8],"engineering":[9],"task":[10],"that":[11,50],"demands":[12],"iterative":[13],"reasoning":[14],"over":[15],"coupled":[16],"performance":[17],"tradeoffs,":[18],"yet":[19],"proprietary":[20,206],"process":[21],"kits":[23],"(PDKs)":[24],"make":[25],"hosted":[26],"large":[27],"language":[28,56],"model":[29,57],"workflows":[30],"difficult":[31],"to":[32,184,208,221],"deploy":[33],"in":[34,97],"practical":[35,199],"settings.":[37],"We":[38,103],"present":[39],"SLIC":[40,63],"(Small":[41],"LM":[42],"Iterating":[43],"on":[44,164],"Circuits),":[45],"reinforcement":[47],"fine-tuning":[48],"framework":[49],"trains":[51],"4B-scale,":[53],"locally":[54],"deployable":[55],"for":[58,89,117],"closed-loop":[59],"analog":[60],"optimization.":[62],"pairs":[64],"structured":[65],"representations":[67],"with":[68,114,128,215],"discretized":[69],"relative-update":[70],"actions,":[71],"domain-":[72],"and":[73,77,93,123,167],"success-gated":[74],"multiobjective":[75],"rewards,":[76],"Reward-Guided":[78],"Rollout":[79],"Steering":[80],"(RGRS),":[81],"which":[82],"turns":[83],"per-step":[84],"simulator":[85,217],"feedback":[86],"into":[87],"signals":[88],"both":[90],"policy":[91],"learning":[92],"online":[94],"rollout":[95],"construction":[96],"this":[98],"sparse,":[99],"highly":[100],"constrained":[101],"domain.":[102],"further":[104,213],"release":[105],"an":[106],"open,":[107],"goal-conditioned":[108],"benchmark":[109],"of":[110],"41":[111],"amplifier":[112],"topologies":[113],"standardized":[115],"protocols":[116],"in-distribution":[118,141],"validation,":[119],"held-out":[120,165],"topology":[121],"evaluation,":[122],"cross-technology-node":[124],"transfer.":[125],"Trained":[126],"solely":[127],"open":[129],"source":[130],"65":[131,188],"nm":[132,189],"CMOS":[133,190],"predictive":[134],"technology":[135,176],"models":[136],"(PTM),":[137],"SLIC-Random":[138,193],"achieves":[139,194],"87.1%":[140],"four-specification":[142],"Pass@1":[143,163,224],"within":[144],"eight":[145],"turns,":[146],"surpassing":[147],"the":[148,157,168],"763B":[149],"DeepSeek-V4.1-Flash":[150],"Think":[151],"by":[152],"48.5":[153],"percentage":[154],"points.":[155],"Beyond":[156],"training":[158],"distribution,":[159],"SLIC-Softmax":[160],"reaches":[161],"72.6%":[162],"topologies,":[166],"trained":[169],"policies":[170],"consistently":[171],"transfer":[172,182],"across":[173],"five":[174],"unseen":[175],"nodes":[177],"without":[178,204],"additional":[179],"fine-tuning.":[180],"This":[181],"extends":[183],"commercial":[186],"TSMC":[187],"PDK,":[191],"where":[192],"49.9%":[195],"held-out-topology":[196,223],"Pass@1,":[197],"demonstrating":[198],"deployment":[200],"through":[201],"local":[202],"inference":[203],"transmitting":[205],"data":[207],"external":[209],"LLM":[210],"services.":[211],"Performance":[212],"scales":[214],"test-time":[216],"interactions,":[218],"reaching":[219],"up":[220],"83.2%":[222],"at":[225],"32-turn":[227],"budget.":[228]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}