Reproduce “Game-Theoretic Co-Evolution for LLM-Based Heuristic Discovery” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Xinyi Ke, Kai Li, Junliang Xing, Yifan Zhang, Jian Cheng
ASRO co-evolves solver and instance-generator programs for hard optimization problems, using pools of accumulated strategies and mixed strategies to guide repeated searches for approximate best responses. Unlike fixed-distribution evaluation, its generator adapts to challenge the solver. On online bin packing’s Hard28 ascending-size benchmark, ASRO-EoH reaches a 12.45% gap versus 40.02% for EoH; this result is benchmark-specific.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.