SolSearch: An LLM-Driven Framework for Efficient SAT-Solving Code Generation

2025-02-20

AI Summary

This work addresses the efficiency bottleneck of SAT solvers in software engineering applications—such as program verification and configuration management—by proposing the first LLM-driven, plug-and-play SAT strategy search framework. Methodologically, it integrates a curriculum-based trial-and-error mechanism, iterative code generation and evaluation, and an abstracted, unified solver interface enabling seamless integration of arbitrary existing SAT solvers. Its key contribution lies in closing the SAT solver design loop with large language models, automating collaborative strategy exploration, code synthesis, and performance feedback. Evaluated on standard SAT benchmarks, the framework-generated optimized solvers outperform state-of-the-art approaches: Z3 achieves an 11% improvement in PAR-2 score. This constitutes the first empirical validation of AI-native enhancement for symbolic solver design, demonstrating both effectiveness and generalizability across solver backends.

Technology Category

• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Search and Optimization: Sampling/Simulation-based Search
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

The Satisfiability (SAT) problem is a core challenge with significant applications in software engineering, including automated testing, configuration management, and program verification. This paper presents SolSearch, a novel framework that harnesses large language models (LLMs) to discover and optimize SAT-solving strategies automatically. Leveraging a curriculum-based, trial-and-error process, SolSearch enables the LLM to iteratively modify and generate SAT solver code, thereby improving solving efficiency and performance. This automated SAT-solving paradigm has the advantage of being plug-and-play, allowing integration with any SAT solver and accelerating the development or design process of new SAT solvers (new methods). Our preliminary experimental results are encouraging by demonstrating that the LLM-powered paradigm improves state-of-the-art SAT solvers on general SAT benchmarks and significantly enhances the performance of the widely used Z3 solver (11% on PAR-2 score). These results highlight the potential for using LLM-driven methods to advance solver adaptability and effectiveness in real-world software engineering challenges. Future research directions are discussed to further refine and validate this approach, offering a promising avenue for integrating AI with traditional software engineering tasks.

Problem

• Automates SAT-solving code generation using LLMs
• Improves efficiency of SAT solvers via iterative optimization
• Enhances Z3 solver performance by 11% on benchmarks

Innovation

• LLM-driven SAT-solving
• Curriculum-based code generation
• Plug-and-play solver integration