RoCo: Role-Based LLMs Collaboration for Automatic Heuristic Design

TL;DR

RoCo introduces a multi-agent, role-based system leveraging collaborative LLMs to automatically design heuristics for combinatorial optimization, significantly improving performance over existing methods.

Contribution

The paper presents RoCo, a novel multi-agent framework with specialized roles that enhances heuristic design quality through structured collaboration and feedback among LLM-guided agents.

Findings

RoCo outperforms existing heuristic methods on five COPs.

The multi-role collaboration improves heuristic diversity and quality.

RoCo demonstrates robustness in both white-box and black-box settings.

Abstract

Automatic Heuristic Design (AHD) has gained traction as a promising solution for solving combinatorial optimization problems (COPs). Large Language Models (LLMs) have emerged and become a promising approach to achieving AHD, but current LLM-based AHD research often only considers a single role. This paper proposes RoCo, a novel Multi-Agent Role-Based System, to enhance the diversity and quality of AHD through multi-role collaboration. RoCo coordinates four specialized LLM-guided agents-explorer, exploiter, critic, and integrator-to collaboratively generate high-quality heuristics. The explorer promotes long-term potential through creative, diversity-driven thinking, while the exploiter focuses on short-term improvements via conservative, efficiency-oriented refinements. The critic evaluates the effectiveness of each evolution step and provides targeted feedback and reflection. The integrator synthesizes proposals from the explorer and exploiter, balancing innovation and exploitation to drive overall progress. These agents interact in a structured multi-round process involving feedback, refinement, and elite mutations guided by both short-term and accumulated long-term reflections. We evaluate RoCo on five different COPs under both white-box and black-box settings. Experimental results demonstrate that RoCo achieves superior performance, consistently generating competitive heuristics that outperform existing methods including ReEvo and HSEvo, both in white-box and black-box scenarios. This role-based collaborative paradigm establishes a new standard for robust and high-performing AHD.