6 papers
Right Answer, Wrong Method: Shortcut Hacking Misleads the Evaluation of LLM Reasoning on Frontier Science Benchmarks
Xuan Ren, Weiqi Zhai, Tianle Pu +3
Scientific reasoning benchmarks typically evaluate large language models (LLMs) using final-answer accuracy. However, a correct answer does not necessarily demonstrate the reasonin…
A2DEPT: Large Language Model-Driven Automated Algorithm Design via Evolutionary Program Trees
Bin Chen, Shouliang Zhu, Beidan Liu +4
Designing heuristics for combinatorial optimization problems (COPs) is a fundamental yet challenging task that traditionally requires extensive domain expertise. Recently, Large La…
Learn to Relax with Large Language Models: Solving Constraint Optimization Problems via Bidirectional Coevolution
Beidan Liu, Zhengqiu Zhu, Chen Gao +4
Large Language Model (LLM)-based optimization has recently shown promise for autonomous problem solving, yet most approaches still cast LLMs as passive constraint checkers rather t…
Optimizing p-spin models through hypergraph neural networks and deep reinforcement learning
Li Zeng, Mutian Shen, Tianle Pu +5
p-spin glasses, characterized by frustrated many-body interactions beyond the conventional pairwise case (p>2), are prototypical disordered systems whose ground-state search is NP-…
CoCo-MILP: Inter-Variable Contrastive and Intra-Constraint Competitive MILP Solution Prediction
Tianle Pu, Jianing Li, Yingying Gao +5
Mixed-Integer Linear Programming (MILP) is a cornerstone of combinatorial optimization, yet solving large-scale instances remains a significant computational challenge. Recently, G…
RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domains
Tianle Pu, Zijie Geng, Haoyang Liu +5
Mixed-Integer Linear Programming (MILP) is a fundamental and powerful framework for modeling complex optimization problems across diverse domains. Recently, learning-based methods…