arXiv subjects

Mengyuan Zhong

Publications and source records attributed to Mengyuan Zhong.

4 recordsLinked to original sources

arXiv2026

HiFo-Prompt: Prompting with Hindsight and Foresight for LLM-based Automatic Heuristic Design

LLM-based Automatic Heuristic Design (AHD) within Evolutionary Computation (EC) frameworks has shown promising results. However, its effectiveness is hindered by the use of static operators and the lack of knowledge accumulation mechanisms. We introduce HiFo-Prompt, a framework that guides LLMs with two synergistic prompting strategies: Foresight and Hindsight. Foresight-based prompts adaptively steer the search based on population dynamics, managing the exploration-exploitation trade-off. In addition, hindsight-based prompts mimic human expertise by distilling successful heuristics from past generations into fundamental, reusable design principles. This dual mechanism transforms transient discoveries into a persistent knowledge base, enabling the LLM to learn from its own experience. Empirical results demonstrate that HiFo-Prompt significantly outperforms state-of-the-art LLM-based AHD methods, generating higher-quality heuristics while achieving substantially faster convergence and superior query efficiency. Our code is available at https://github.com/Challenger-XJTU/HiFo-Prompt.

cs.AI↗

arXiv2026

TIDE: Tuning-Integrated Dynamic Evolution for LLM-Based Automated Heuristic Design

Although Large Language Models have advanced Automated Heuristic Design, treating algorithm evolution as a monolithic text generation task overlooks the coupling between discrete algorithmic structures and continuous numerical parameters. Consequently, existing methods often discard promising algorithms due to uncalibrated constants and suffer from premature convergence resulting from simple similarity metrics. To address these limitations, we propose TIDE, a Tuning-Integrated Dynamic Evolution framework designed to decouple structural reasoning from parameter optimization. TIDE features a nested architecture where an outer parallel island model utilizes Tree Similarity Edit Distance to drive structural diversity, while an inner loop integrates LLM-based logic generation with a differential mutation operator for parameter tuning. Additionally, a UCB-based scheduler dynamically prioritizes high-yield prompt strategies to optimize resource allocation. Extensive experiments across nine combinatorial optimization problems demonstrate that TIDE discovers heuristics that significantly outperform state-of-the-art baselines in solution quality while achieving improved search efficiency and reduced computational costs.

cs.AI↗

arXiv2025

Learning to Insert for Constructive Neural Vehicle Routing Solver

Neural Combinatorial Optimisation (NCO) is a promising learning-based approach for solving Vehicle Routing Problems (VRPs) without extensive manual design. While existing constructive NCO methods typically follow an appending-based paradigm that sequentially adds unvisited nodes to partial solutions, this rigid approach often leads to suboptimal results. To overcome this limitation, we explore the idea of insertion-based paradigm and propose Learning to Construct with Insertion-based Paradigm (L2C-Insert), a novel learning-based method for constructive NCO. Unlike traditional approaches, L2C-Insert builds solutions by strategically inserting unvisited nodes at any valid position in the current partial solution, which can significantly enhance the flexibility and solution quality. The proposed framework introduces three key components: a novel model architecture for precise insertion position prediction, an efficient training scheme for model optimization, and an advanced inference technique that fully exploits the insertion paradigm's flexibility. Extensive experiments on both synthetic and real-world instances of the Travelling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP) demonstrate that L2C-Insert consistently achieves superior performance across various problem sizes.

cs.LG↗

arXiv2025

Weyl Semimetals: from Principles, Materials to Applications

Weyl semimetals have attracted significant interest in condensed matter physics and materials science, due to their unique electronic and topological properties. These characteristics not only deepen our understanding of fundamental quantum phenomena, but also make Weyl semimetals promising candidates for advanced applications in electronics, photonics, and spintronics. This review provides a systematic overview of the field, covering theoretical foundations, material synthesis, engineering strategies, and emerging device applications. We first outline the key theoretical principles and distinctive properties of Weyl semimetals, followed by an examination of recent advancements that enhance their functional versatility. Finally, we discuss the critical challenges hindering their practical implementation and explore future development directions, along with the potential for expanding and enhancing their existing range of applications. By integrating discussions of both opportunities and obstacles, this review offers a balanced perspective on current progress and future directions in Weyl semimetal research.

cond-mat.mtrl-sci↗