A-IC3: Learning-Guided Adaptive Inductive Generalization for Hardware Model Checking

2026-04-23

AI Summary

This work addresses the limitations of traditional IC3 algorithms, whose static strategies in the inductive generalization phase struggle to adapt to the dynamic context of verification, thereby constraining clause quality and verification efficiency. To overcome this, the paper introduces an online learning mechanism into the IC3 framework for the first time, proposing a lightweight multi-armed bandit (MAB) approach that dynamically selects the optimal generalization strategy based on real-time feedback. By continuously evaluating generalization outcomes to refine strategy selection, the method achieves context-aware, adaptive inductive generalization. Experimental results on 914 HWMCC benchmark instances demonstrate that the proposed approach solves 26 to 50 more instances than baseline methods and improves PAR-2 scores by 194.72 to 389.29, significantly outperforming existing techniques.

Technology Category

• Machine Learning: Online Learning & Bandits
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

The IC3 algorithm represents the state-of-the-art (SOTA) hardware model checking technique, owing to its robust performance and scalability. A significant body of research has focused on enhancing the solving efficiency of the IC3 algorithm, with particular attention to the inductive generalization process: a critical phase wherein the algorithm seeks to generalize a counterexample to inductiveness (CTI), which typically is a state leading to a bad state, into a broader set of states. This inductive generalization is a primary source of clauses in IC3 and thus plays a pivotal role in determining the overall effectiveness of the algorithm. Despite its importance, existing approaches often rely on fixed inductive generalization strategies, overlooking the dynamic and context-sensitive nature of the verification environment in which spurious counterexamples arise. This rigidity can limit the quality of generated clauses and, consequently, the performance of IC3. To address this limitation, we propose a lightweight machine-learning-based framework that dynamically selects appropriate inductive generalization strategies in response to the evolving verification context. Specifically, we employ a multi-armed bandit (MAB) algorithm to adaptively choose inductive generalization strategies based on real-time feedback from the verification process. The agent is updated by evaluating the quality of generalization outcomes, thereby refining its strategy selection over time. Empirical evaluation on a benchmark suite comprising 914 instances, primarily drawn from the latest HWMCC collection, demonstrates the efficacy of our approach. When implemented on the state-of-the-art model checker rIC3, our method solves 26 to 50 more cases than the baselines and improves the PAR-2 score by 194.72 to 389.29.

Problem

• IC3
• inductive generalization
• hardware model checking
• counterexample to inductiveness
• verification context

Innovation

• inductive generalization
• multi-armed bandit
• adaptive strategy
• hardware model checking
• IC3