Skip to content
Preprint

Agentic-IC3: Enabling Semantic Proof Search in IC3 Model Checking

Sep 2026 · 0 citations · 27 references
Computer Science

TL;DR

Agentic-IC3 is presented, built on Pono's word-level model-checking infrastructure, which integrates a language-model agent into IC3 to guide semantic proof search using register-transfer-level (RTL) design information.

Abstract

IC3 is a state-of-the-art algorithm for hardware model checking that proves safety properties by incrementally constructing an inductive invariant consisting of a set of lemmas. Its effectiveness depends on generalization heuristics that identify useful lemmas and guide proof search. However, many leading IC3 hardware model checkers operate on lowered, bit-level representations, where high-level design relationships are difficult to exploit for generalization. Those operating at a higher level remain limited in exploiting high-level design structure and semantics. We present Agentic-IC3, built on Pono's word-level model-checking infrastructure, which integrates a language-model agent into IC3 to guide semantic proof search using register-transfer-level (RTL) design information. The framework exposes an agent-oriented interface to a persistent IC3 backend, allowing the agent to interact with an explicit, evolving proof state throughout verification. Across successive proof obligations, the agent relates intermediate proof states and solver feedback to the RTL and proposes high-level lemmas through both SAT and UNSAT generalization. Beyond generalization, the agent can introduce derived observation signals to express design relationships succinctly and obtain more informative feedback, and backtrack to revise proposals that lead to unproductive proof branches. The backend checks proposals before updating the proof state, preserving soundness and providing feedback for further reasoning. On a suite of 14 benchmarks spanning security information-flow verification and functional verification of communication protocols, processors, and functional units, Agentic-IC3 solves 10 cases within a one-hour timeout, including 4 unsolved by all three evaluated baselines: rIC3, Pono-IC3Bits, and A-IC3.

View source

Similar papers

Preprint Oct 2026

Symbolic Search Is Not Exhausted: Persistent Proof-Space Exploration in Lean4

Formal theorem proving increasingly combines learned semantic guidance with verified symbolic execution. The quality of the symbolic search substrate therefore determines how much useful mathematical structure can be accumulated, reused, and exposed under a finite inference budget. We introduce ViaLean, a Lean4 prover...

Ruoran Xu · 0 citations
#artificial intelligence Preprint Oct 2026

Cost-Efficient Theorem Proving via Agent Orchestration in Program Verification

Program verification establishes software correctness through machine-checkable proofs constructed in theorem provers. It's a guarantee especially valuable for code generated by large language models (LLMs), which is fluent but carries no assurance of correctness. Almost all existing provers, however, pursue pass rates...

Shuang-Jie Yao, Nikolaus Holzer, Mark Santolucito et al. · 0 citations
Preprint Aug 2026

Schwarz: Solver-Aware Agentic Program Verification

Agentic verification systems can often generate source-level specifications that look plausible, but plausibility is not enough: the verifier must still turn those specifications into SMT obligations that the solver can prove. When this step fails, current LLM-driven loops usually expose only a coarse verifier error, t...

Jing-Yu Ke, Ling-I Wu, Guoqiang Li · 0 citations
Open access Sep 2026

Modelling Shared-Space Coordination in mCRL2: a Bach-to-mCRL2 Translation Framework

Although significant research has focused on the theory and implementation of data-based coordination languages, the critical aspect of their automated verification using model-checking techniques remains underexplored, which is essential for ensuring reliability and correctness in distributed systems. Existing tools,...

Corentin Reuther, Jean-Marie Jacquet · 0 citations
#artificial intelligence Review Oct 2026

SCOPE: Certified Theorem Proving with a Language Model as the Policy Planner

In proof assistants such as Lean, a generated proof must pass machine compilation checks, so evaluation needs no human scoring. Direct generation fails on multi-step numeric propositions: a proof is valid only if every content integer is correct, so the pass rate is bounded by the k-th power of the per-integer accuracy...

Han Zhou, Jia-Le Li · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.