AutoPBO: LLM-powered Optimization for Local Search PBO Solvers

2025-09-04

AI Summary

Local search solvers for Pseudo-Boolean Optimization (PBO) traditionally rely on manually engineered heuristics, limiting adaptability and requiring expert intervention. Method: This work introduces the first LLM-augmented framework for PBO, leveraging prompt engineering and feedback-driven refinement to automatically generate and optimize key heuristics—including neighborhood selection and variable flipping—without modifying the underlying search logic. By interpreting PB constraint semantics, the LLM dynamically adapts heuristics to problem structure. Contribution/Results: Evaluated on four standard benchmarks, our approach significantly outperforms specialized local search solvers (e.g., NuPBO, OraSLS) and matches or approaches the performance of state-of-the-art general-purpose MIP solvers (e.g., Gurobi, SCIP) on multiple instances. It substantially reduces reliance on human expertise, establishing a novel paradigm for intelligent, data-informed evolution of combinatorial optimization solvers.

Technology Category

• Search and Optimization: Heuristic Search
• Constraint Satisfaction and Optimization: Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• 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: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Pseudo-Boolean Optimization (PBO) provides a powerful framework for modeling combinatorial problems through pseudo-Boolean (PB) constraints. Local search solvers have shown excellent performance in PBO solving, and their efficiency is highly dependent on their internal heuristics to guide the search. Still, their design often requires significant expert effort and manual tuning in practice. While Large Language Models (LLMs) have demonstrated potential in automating algorithm design, their application to optimizing PBO solvers remains unexplored. In this work, we introduce AutoPBO, a novel LLM-powered framework to automatically enhance PBO local search solvers. We conduct experiments on a broad range of four public benchmarks, including one real-world benchmark, a benchmark from PB competition, an integer linear programming optimization benchmark, and a crafted combinatorial benchmark, to evaluate the performance improvement achieved by AutoPBO and compare it with six state-of-the-art competitors, including two local search PBO solvers NuPBO and OraSLS, two complete PB solvers PBO-IHS and RoundingSat, and two mixed integer programming (MIP) solvers Gurobi and SCIP. AutoPBO demonstrates significant improvements over previous local search approaches, while maintaining competitive performance compared to state-of-the-art competitors. The results suggest that AutoPBO offers a promising approach to automating local search solver design.

Problem

• Automating heuristic design for PBO local search solvers
• Reducing manual expert effort in solver optimization
• Enhancing solver performance using LLM-powered framework

Innovation

• LLM-powered framework for PBO solvers
• Automatically enhances local search heuristics
• Improves performance across multiple benchmarks