cs.NEcs.AI
Performance and Explainability Requirements of Evolutionary Algorithms in Real-World Physics-Informed Optimization
May 27, 2026
This paper analyzes the performance and explainability requirements of evolutionary algorithms when applied to complex, real-world physics-informed optimization problems, identifying a gap between current research and practical application.
Evolutionary computation offers a variety of tools to solve complex real-world optimization problems. However, research often focuses on smaller, simplified problems and optimization algorithms that sometimes miss expectations in real-world scenarios. Additionally, trust in the applied algorithm and the solutions it provides is often essential in such settings, but requires an understanding of the search process itself. This leads to evolutionary computation often not being seriously considered by practitioners in many application contexts, among them physics-based modeling. In this article, techniques from evolutionary computation are detailed that can alleviate these problems. First, five real-world physics-based optimization problems are introduced and described by domain experts. For each of these, the requirements for the evolutionary algorithm regarding performance and explainability to increase trust and usability are presented. We found that all domain experts expect fast convergence to a good solution and want some explanations for how the results were formed, while other requirements strongly depend on the respective problem. Finally, we present existing approaches that can be leveraged to improve those aspects of evolutionary algorithms but have to our knowledge never been employed in complex real-world scenarios. This implies a gap between both domains that needs to be closed to exploit the full potential of evolutionary computation.
Do Physics Foundation Models Learn Generalizable Physics? A Bias-Aware Benchmark Across Physical Reg…
The paper introduces a comprehensive benchmark to test if physics foundation mod…
NewtPhys: Do Foundation Models Understand Newtonian Physics?
The paper introduces NewtPhys, a novel 4D dataset of real-world scenes with dens…
Sample-efficient Low-level Motion Planning for Robotic Manipulation Tasks via Zero-shot Transfer Lea…
The paper proposes an iCEM+TL framework that combines the Sample-efficient Cross…
Domain-Informed Representation for Evolutionary Sieving in Integral and Module Lattices
This paper enhances a genetic algorithm approach for solving the Shortest Vector…
X4Val: Learning Neural Surrogates for Variance-Reduced Policy Evaluation
This paper introduces X4Val, a framework for variance-reduced real-world metric…
BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterou…
BORA is an offline-to-online RL framework that enhances dexterous VLA models for…
Towards fast computation of higher discrete homology
The paper presents a novel and significantly faster algorithm for computing the…
Evolutionary Discovery of Bivariate Bicycle Codes with LLM-Guided Search
The paper introduces an LLM-guided evolutionary workflow that successfully disco…