LLM-driven AAD
We are excited to announce the Large Language Model driven Automated Algorithm Design with Evolutionary Computing tutorial at PPSN 2026.
Large language models (LLMs) are transforming the way we create and automate AI techniques and algorithm discoveries. This shift moves us beyond just hyperparameter tuning and automated selection into the realms of fully automated algorithm design (AAD), architecture and end-to-end pipeline discovery, effectively closing the loop between ideation and evaluation.
This tutorial provides an overview of the rapidly evolving landscape, including frameworks like EASE, LLaMEA, LHNS, MCTS-AHD, PartEVO, AlphaEvolve, and FunSearch. We specifically contrast two of our own-developed frameworks: the architecture of EASE (Effortless Algorithmic Solution Evolution) with the evolutionary-focused approach of LLaMEA (Large Language Model Evolutionary Algorithm). We will explore EASE as a practical, fully modular framework for iterative, closed-loop generation and evaluation. Beyond just algorithm code, EASE can also iteratively generate text and graphics. Following that, the tutorial will shift its focus to the LLaMEA framework and its connection with the benchmarking ecosystem IOH, recent advancements including the hyperparameter optimization toolkit LLaMEA-HPO & LLaMEA-BO, and the unique benchmarking suite for automated algorithm discovery – BLADE.
Participants in this tutorial will have a unique opportunity to learn about two seemingly competing frameworks in one place, and discover how to collaborate effectively in this rapidly developing area, complementing partial knowledge for greater efficiency and global deployment of these frameworks for AAD.
The format of the tutorial is demo-driven (no hands-on activities): we will feature short videos and narrated walkthroughs of the EASE frontend and backend and LLaMEA examples. These will illustrate task setup, fitness and evaluation loops, and result inspection. Additionally, we will provide links to EASE/LLaMEA variants, documentation, and benchmarking environments.
We will highlight key guardrails, including testing, analysis, and time/resource caps, as well as best practices in evaluation and benchmarking. Attendees will emerge with practical criteria for choosing between LLaMEA and EASE, methods for responsible evaluation, and steps for incorporating LLM-driven discovery into AI research.
Building upon these frameworks, we will further discuss the orchestration problem — how ensembles of small and large language models can cooperatively drive algorithmic discovery. We will also demonstrate how human-in-the-loop co-discovery mechanisms can inject domain expertise and interpretability into this process, ensuring that automated exploration remains guided, explainable, and auditable. Finally, we will introduce statistical validation methods that ground algorithmic discovery in rigorous evidence — embedding Bayesian comparison, stochastic dominance tests, and sequential evaluation directly into workflows. Together, these ideas chart a practical path toward automated algorithm design systems that both generate and justify new algorithms.
Previous Editions
Organizers:
