5 papers
Bi-EZP: LLM-Guided Bilevel Program Evolution for Ensemble Zero-Cost Proxy Discovery
Yutao Lai, Kezhao Lai, Hai-Lin Liu
Zero-cost proxies enable neural architecture search (NAS) to rank candidate networks from statistics computed at initialization, avoiding repeated training. However, different prox…
SpecAHD: Localize to Specialize for Automated Heuristic Design in Large-Scale Routing Problems
Kezhao Lai, Yutao Lai, Hai-Lin Liu
LLM-based automated heuristic design (AHD) typically scores executable programs on complete instances or within fixed solver components. In large-scale routing problems, localized…
Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games
Yidong He, Yutao Lai, Pengxu Yang +4
While Large Language Models (LLMs) excel in certain reasoning tasks, they struggle in multi-agent games where the final outcome depends on the joint strategies of all agents. In mu…
Beyond the Node: Clade-level Selection for Efficient MCTS in Automatic Heuristic Design
Kezhao Lai, Yutao Lai, Hai-Lin Liu
While Monte Carlo Tree Search (MCTS) shows promise in Large Language Model (LLM) based Automatic Heuristic Design (AHD), it suffers from a critical over-exploitation tendency under…
SEKI: Self-Evolution and Knowledge Inspiration based Neural Architecture Search via Large Language Models
Zicheng Cai, Yaohua Tang, Yutao Lai +3
We introduce SEKI, a novel large language model (LLM)-based neural architecture search (NAS) method. Inspired by the chain-of-thought (CoT) paradigm in modern LLMs, SEKI operates i…