{"type":"ScholarlyArticle","title":"Large Lemma Miners: Can LLMs Do Induction Proofs for Hardware?","authors":[{"name":"Romy Peled","slug":"romy-peled","given":"Romy","family":"Peled","affiliation":""},{"name":"Daniel Kroening","slug":"daniel-kroening","given":"Daniel","family":"Kroening","affiliation":""},{"name":"Michael Tautschnig","slug":"michael-tautschnig","given":"Michael","family":"Tautschnig","affiliation":""},{"name":"Yakir Vizel","slug":"yakir-vizel","given":"Yakir","family":"Vizel","affiliation":""}],"abstract":"Large Language Models (LLMs) have shown potential for solving mathematical tasks.\r\nWe show that LLMs can be utilized to generate proofs by induction for hardware verification and thereby replace some of the manual work %alleviating some of the manual effort\r\ndone by Formal Verification engineers and deliver value to industry.\r\nWe present a neurosymbolic approach that includes two prompting frameworks to generate candidate invariants, which are checked using a formal symbolic tool.\r\nOur results indicate that with sufficient reprompting, LLMs are able to generate inductive arguments for mid-size open-source RTL designs. For\r\n90% of our problem set, at least one of the prompt setups succeeded in producing a provably correct inductive argument.","doi":"10.24963/ijcai.2026/444","url":"https://ijcai.org/proceedings/2026/444","pdf":"https://ijcai.org/proceedings/2026/0444.pdf","markdown":"https://ijcai.org/proceedings/2026/444.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/444","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Knowledge Representation and Reasoning","track":"Main Track","number":444,"pages":{"first":3988,"last":3998},"keywords":["Natural Language Processing: Language models","Natural Language Processing: Applications","Knowledge Representation and Reasoning: Automated reasoning and theorem proving"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}