DyACE: Dynamic Algorithm Co-evolution for Online Automated Heuristic Design with Large Language Model

TL;DR

DyACE introduces a dynamic, LLM-guided co-evolution framework for heuristic algorithms, enabling real-time adaptation to search landscape changes and outperforming static methods in combinatorial optimization.

Contribution

This paper presents DyACE, a novel approach that models heuristic design as a non-stationary control problem, utilizing LLMs and look-ahead feedback for adaptive algorithm co-evolution.

Findings

DyACE outperforms static baselines on three benchmarks.

Dynamic adaptation improves search efficiency in high-dimensional spaces.

Grounded perception is essential for effective heuristic adaptation.

Abstract

The prevailing paradigm in Automated Heuristic Design (AHD) typically relies on the assumption that a single, fixed algorithm can effectively navigate the shifting dynamics of a combinatorial search. This static approach often proves inadequate for Perturbative Heuristics, where the optimal algorithm for escaping local optima depends heavily on the specific search phase. To address this limitation, we reformulate heuristic design as a Non-stationary Bi-level Control problem and introduce DyACE (Dynamic Algorithm Co-evolution). Distinct from standard open-loop solvers, DyACE use a Receding Horizon Control architecture to continuously co-evolve the heuristic logic alongside the solution population. A core element of this framework is the Look-Ahead Rollout Search, which queries the landscape geometry to extract Search Trajectory Features. This sensory feedback allows the Large Language Model (LLM) to function as a grounded meta-controller, prescribing phase-specific interventions tailored to the real-time search status. We validate DyACE on three representative combinatorial optimization benchmarks. The results demonstrate that our method significantly outperforms state-of-the-art static baselines, exhibiting superior scalability in high-dimensional search spaces. Furthermore, ablation studies confirm that dynamic adaptation fails without grounded perception, often performing worse than static algorithms. This indicates that DyACE's effectiveness stems from the causal alignment between the synthesized logic and the verified gradients of the optimization landscape.