Coverage-Driven RTL Assertion Generation with Formal Exploration and Neuro-Symbolic Refinement

The paper introduces NeuroAssertion, a coverage-driven framework for generating RTL assertions that integrates formal trace generation, syntax-guided synthesis, and a two-step large language model (LLM) refinement process. It transforms hard-to-reach control-flow conditions into formal reachability goals, uses model checking to produce diverse traces, and mines initial assertions via SyGuS. The refinement stage employs one LLM to propose candidate assertions for uncovered regions and a second LLM to generate repair grammars that guide symbolic synthesis, resulting in roughly twice as many assertions and higher mutation coverage compared to traditional methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents