{"paper":{"title":"Alpha-RTL: Test-Time Training for RTL Hardware Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cangyuan Li, Haoyu Gao, Kaiyan Chang, Peilong Zhou, Ying Wang, Zhirong Chen, Ziming Qu","submitted_at":"2026-06-03T14:51:33Z","abstract_excerpt":"Large language models (LLMs) have shown increasing promise in generating\n  functionally correct register-transfer-level (RTL) hardware designs.\n  Recent systems improve further through EDA-integrated reinforcement\n  learning with syntax, simulation, and PPA rewards, but train a general\n  RTL generator before deployment while test-time approaches search with\n  a frozen policy. We instead perform reinforcement learning at test time,\n  allowing the LLM policy to adapt to executable EDA feedback for the\n  specific RTL problem at hand. We propose TTT-RTL, to our knowledge the\n  first per-design tes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05253","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.05253/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}