Lars
Quaedvlieg

Anja Surina , Amin Mansouri , Lars Quaedvlieg , Amal Seddas , Maryna Viazovska , Emmanuel Abbe , Caglar Gulcehre

Conference on Language Modeling (COLM) · 2025

Discovering efficient algorithms for solving complex problems has been an outstanding challenge in mathematics and computer science, requiring substantial human expertise over the years. Recent advancements in evolutionary search with large language models (LLMs) have shown promise in accelerating the discovery of algorithms across various domains, particularly in mathematics and optimization. However, existing approaches treat the LLM as a static generator, missing the opportunity to update the model with the signal obtained from evolutionary exploration. In this work, we propose to augment LLM-based evolutionary search by continuously refining the search operator - the LLM - through reinforcement learning (RL) fine-tuning. Our method leverages evolutionary search as an exploration strategy to discover improved algorithms, while RL optimizes the LLM policy based on these discoveries. Our experiments on three combinatorial optimization tasks - bin packing, traveling salesman, and the flatpack problem - show that combining RL and evolutionary search improves discovery efficiency of improved algorithms, showcasing the potential of RL-enhanced evolutionary strategies to assist computer scientists and mathematicians for more efficient algorithm design.

Lars Quaedvlieg ^* , Andrea Miele ^* , Caglar Gulcehre

International Conference on Machine Learning (ICML) CodeML Workshop · 2025

^* equal contribution

Producing publication-quality visualizations and tables for machine learning papers is often tedious, time-consuming, and prone to inconsistencies. We introduce Swizz, a lightweight Python library designed specifically for researchers to effortlessly generate elegant figures, LaTeX-ready tables, and customizable figure layouts with minimal code. Swizz enables one-line creation of consistent, conference-ready visualizations, including advanced plots and multilevel tables, and provides intuitive, composable layouts to simplify complex figure arrangements. Its automated styling and built-in visual gallery facilitate rapid experimentation, allowing researchers to focus more on research and less on formatting. Swizz is publicly available, easy to integrate into existing workflows, and is themed for major machine learning publication venues. Swizz is open source (MIT) and is available on GitHub and PyPI.

Lars Quaedvlieg

arXiv preprint arXiv:2501.19063 · 2025

Efficient job allocation in complex scheduling problems poses significant challenges in real-world applications. In this report, we propose a novel approach that leverages the power of Reinforcement Learning (RL) and Graph Neural Networks (GNNs) to tackle the Job Allocation Problem (JAP). The JAP involves allocating a maximum set of jobs to available resources while considering several constraints. Our approach enables learning of adaptive policies through trial-and-error interactions with the environment while exploiting the graph-structured data of the problem. By leveraging RL, we eliminate the need for manual annotation, a major bottleneck in supervised learning approaches. Experimental evaluations on synthetic and real-world data demonstrate the effectiveness and generalizability of our proposed approach, outperforming baseline algorithms and showcasing its potential for optimizing job allocation in complex scheduling problems.