Tag
The paper introduces Iterative Sequential Transfer (IST) to address knowledge transfer challenges in few-shot multiobjective multitask optimization under tight evaluation budgets, using likelihood-informed task prioritization.
MOAE proposes a Pareto-preserving evolutionary search method to simultaneously optimize multiple objectives like task performance, trajectory quality, and safety for LLM agents without fixed scalarization during search.
Introduces ELMER, an evolutionary language model that searches over natural-language policy descriptions and compiles them into executable programs, using fine-tuned Qwen3-8B with Direct Preference Optimization to control mutation strength and improve search efficiency.
This paper proposes a method that uses large language models to generate new features from tabular data via an evolutionary algorithm, demonstrating improved classification results across multiple datasets.
Introduces RL-NSGA-II-GRC, a method integrating reinforcement learning with the NSGA-II genetic algorithm enhanced by gray relational coefficients for multi-objective optimization, applied to NASDAQ portfolio optimization. Achieves improved convergence and diversified Pareto fronts.
Proposes a closed-loop evolutionary algorithm that guides LLMs to generate complete, executable PINN configurations, reducing mean-squared error on a one-dimensional multiscale wave equation.
Corbin Braun built an evolutionary A/B thumbnail testing tool that mutates one dimension at a time, rotates thumbnails using an ABBA pattern to avoid bias, and learns winning mutations over multiple rounds.
The paper extends the LLaMEA framework to automatically design multi-objective Bayesian optimization algorithms using large language models as mutation and crossover operators within evolutionary strategies, achieving state-of-the-art accuracy with significantly lower computational cost on synthetic and real-world problems.
Introduces EARLY, an evolutionary framework for evolving multi-reservoir Echo State Networks that outperforms random search on temporal learning tasks and exhibits task-dependent structural differences.
This paper applies the MAP-Elites quality diversity algorithm to procedurally generate diverse and high-quality maps for first-person shooter games, introducing new map representations and metrics.
This paper proposes a hybrid WGAN-GA approach for refining generative graph topologies, using a genetic algorithm to correct residual structural deviations in GAN-based generated graphs, improving realism for synthetic graph synthesis and data augmentation.