COTIA: Concolic Testing with Intelligent Agent

Simulation plays a crucial role in the verification of hardware designs, ensuring that they behave correctly before fabrication. However, traditional simulation methods can be inefficient when dealing with complex designs, especially in corner cases. To mitigate this inefficiency, Concolic testing has emerged as a promising technique, utilizing symbolic execution to guide the simulation process. However, the heuristics used in path exploration for Concolic testing often struggle with local optima, resulting in suboptimal verification outcomes and incomplete coverage of the design space. In this paper, we propose an agent-based framework to dynamically adjust path exploration strategies by leveraging beam search and large language models (LLMs). Experimental results demonstrate that this approach significantly improves branch coverage, especially for hard-to-detect branches, while also optimizing the use of computational resources.

• Publication year

  2025

• Venue

  2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)

• Publication date

  2025-10-26

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1109/ICCAD66269.2025.11240634
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• APE-FV: Concolic Testing for RTL Functional Verification Using Adaptive Path Exploration

  2024cited by this paper
• AutoChip: Automating HDL Generation Using LLM Feedback

  2023cited by this paper
• (Security) Assertions by Large Language Models

  2023cited by this paper
• STSearch: State Tracing-based Search Heuristics for RTL Validation

  2023cited by this paper
• GPT-4 Technical Report

  2023cited by this paper
• Late Breaking Results: Test Selection For RTL Coverage By Unsupervised Learning From Fast Functional Simulation

  2023cited by this paper
• Hybrid Rule-based and Machine Learning System for Assertion Generation from Natural Language Specifications

  2022cited by this paper
• Catalyzing next-generation Artificial Intelligence through NeuroAI

  2022cited by this paper
• Scalable Concolic Testing of RTL Models

  2021influential reference
• Training Neural Network for Machine Intelligence in Automatic Test Pattern Generator

  2021cited by this paper
• Language Models are Few-Shot Learners

  2020cited by this paper
• Chatbot-based assertion generation from natural language specifications

  2019cited by this paper
• Controlled Natural Language Framework for Generating Assertions from Hardware Specifications

  2019cited by this paper
• Automatic Assertion Generation from Natural Language Specifications Using Subtree Analysis

  2019cited by this paper
• Training a Neural Network

  2019cited by this paper
• Pyverilog: A Python-Based Hardware Design Processing Toolkit for Verilog HDL

  2015cited by this paper
• Hardware Verification Using Software Analyzers

  2015cited by this paper
• A Primer on Hardware Security: Models, Methods, and Metrics

  2014cited by this paper
• A Survey of Automated Techniques for Formal Software Verification

  2008cited by this paper
• DART: directed automated random testing

  2005cited by this paper
• CUTE: a concolic unit testing engine for C

  2005cited by this paper
• Symbolic RTL simulation

  2001cited by this paper
• RT-Level ITC'99 Benchmarks and First ATPG Results

  2000cited by this paper
• Intelligent agents: theory and practice

  1995cited by this paper
• Symbolic model checking: 1020 states and beyond

  1989cited by this paper

• No citing papers are available for this paper.