21 papers · ranked by Valyu relevance
Alistair Benford, Per Kristian Lehre
Due to their complex dynamics, combinatorial games are a key test case and application for algorithms that train game playing agents. Among those algorithms that train using self-play are coevolutionary algorithms (CoEAs). However, the successful application of CoEAs for game playing is difficult due to pathological…
Yongkai Chen, Samuel W.K. Wong, S. C. Kou
Protein structure prediction has been revolutionized by AlphaFold, yet a key limitation remains: the challenge of characterizing the multiple conformations adopted by proteins that can switch between different folds. Current prevailing approaches rely on sampling the multiple sequence alignment (MSA) input, either…
Alex Bogdan
Many real-world optimization problems are not naturally homogeneous vectors but composite design objects with heterogeneous parameters: integers, real values, Booleans, categoricals, complex-valued descriptors, and embedding vectors. Standard evolutionary algorithms flatten these into a single chromosome and apply…
Md Zarzees Uddin Shah Chowdhury, T. M. Murali, Palash Sashittal
Advances in metagenomics have rapidly expanded viral discovery, revealing vast diversity across Earth’s virosphere. Yet most virus–host interactions—i.e., which viruses infect which hosts—remain unrecorded. Identifying these interactions is essential for anticipating zoonotic spillover events and advancing biomedical…
Authors not listed
Machine olfaction—the artificial replication of the sense of smell—faces significant challenges due to the absence of large, standardized training datasets. Unlike vision, language, and audio models, which benefit from extensive corpora such as ImageNet, GLUE, and AudioSet, olfaction lacks scaled equivalents and…
Shengnan Li, Taiju Yin, Heming Jia
As engineering systems grow in complexity, reliable metaheuristic optimizers are increasingly essential. While swarm intelligence algorithms are widely applied, recent approaches like the Cuckoo Catfish Optimizer (CCO) can experience premature convergence due to limited local exploitation and simplistic boundary…
Xiaoyu Cao, Yueshun He, Linlin He, Wei Lv + 2 more
3D UAV path planning intends to produce safe, feasible, and optimized flight trajectories in complex 3D environments containing multiple obstacles and coupled constraints. Nevertheless, many existing optimization approaches encounter difficulties when dealing with high-dimensional constrained search spaces, since…
Da Teng, Yunrui Qiu, Gokulakannan Sakthivel, Akashnathan Aranganathan + 2 more
While RNA language models (LMs) have served as foundation models (FMs) to advanced structural prediction, their evaluation relies heavily on supervised downstream tasks. Such tasks can often mask FM inefficiencies and reflect downstream training set memorization. To address this, here we introduce REDIAL (RNA Embedding…
Rong Lv, Guofa Lei, Hanchao Liu, Yuhan Sun + 4 more
Enhancing oil and gas production performance is essential for maintaining the economic sustainability of petroleum enterprises and meeting the increasing global energy requirements. In this context, subsurface production optimization constitutes a fundamental component of strategic reservoir management, directly…
Authors not listed
Finding the most stable adsorption geometry of a flexible molecule on a catalytic surface remains a key challenge due to the high dimensionality and ruggedness of the potential energy surface. We present a Gradient-Enhanced Genetic Algorithm (GE-GA) for the global optimization of adsorbate–surface configurations…
Gang Liu, Yihan Zhu, Jie Chen, Meng Jiang
Large language models hold promise as scientific assistants, yet existing agents either rely solely on algorithm evolution or on deep research in isolation, both of which face critical limitations. Pure algorithm evolution, as in AlphaEvolve, depends only on the internal knowledge of LLMs and quickly plateaus in…
Kangbien Park
Directed evolution of asexual populations is expected to offer a wide range of benefits to humanity. Achieving efficient directed evolution (DE) requires a quantitative formulation of the experimental methodologies—or logics—that can address potential challenges throughout the evolutionary process. In this article, I…
Kaichen Ouyang, Yu, Mingyang, Ke + 11 more
This paper introduces a novel framework linking evolutionary computation to statistical physics by formulating optimization as a statistical phase transition. We propose Wasserstein Evolution (WE), an algorithm based on the Wasserstein gradient flow of a free energy functional, translating the physical competition…
Authors not listed
Designing molecules with specific target properties remains a fundamental challenge in computational chemistry. While existing approaches show promise, most rely on simplified representations like SMILES strings or 2D graphs that lack essential three-dimensional geometric information. We present EvoDiffMol, a…
Csenge Petak, Lapo Frati, Renske M. A. Vroomans, Melissa H. Pespeni + 1 more
Title: Significance The speed and direction of evolution depend on the availability of phenotypic variation. Genotype-to-phenotype maps can, over time, bias phenotypic variability to more readily produce alternative adaptive phenotypes in fluctuating environments. However, because properties of the fitness landscapes…
Nam Hai Le
The gene-centric paradigm, formalized in the Modern Synthesis and operationalized through genetic algorithms, attributes evolutionary causality exclusively to genes; organisms are passive vehicles for genetic replication. Denis Noble's phenotype-first framework challenges this view, arguing that organisms are active…
Niki van Stein, Anna V. Kononova, Lars Kotthoff, Thomas Bäck
Large language models have enabled automated algorithm design (AAD) by generating optimization algorithms directly from natural-language prompts. While evolutionary frameworks such as LLaMEA demonstrate strong exploratory capabilities across the algorithm design space, their search dynamics are entirely driven by…
Zahraa Elsayed Mohamed, Walid Dabour
This study proposes a hybrid variant of Elephant Herding Optimization that combines an adaptive clan-updating schedule, Lévy-flight exploration from Cuckoo Search, and elite opposition-based sampling. The design targets three known limitations-premature convergence, imbalance between exploration and exploitation, and…
Inès Benito, Johannes F. Lutzeyer, Benjamin Doerr
Baldwinian and Lamarckian evolution have existed for a long time in evolutionary algorithms (EAs) without ever dominating the academic literature or practical applications. In this work, we use modern empirical and theoretical methods to revisit Lamarckian and Baldwinian evolution and rigorously compare them with the…
Vaibhav Mohanty, Anna Sappington, Eugene I. Shakhnovich, Bonnie Berger
Classical population genetics has largely relied on the same stochastic differential equations (SDEs) for over 60 years to describe evolutionary dynamics. However, these SDEs ignore the fact that phenotype heterogeneity and noise are ubiquitous in biological systems from bacteria to cancers. Here, we develop…
Ata G. Zare
The dominant artificial intelligence paradigm trains neural architectures via gradient descent against proxy objectives and reinforcement learning from human feedback. While remarkably capable, this top-down optimization inherently generates structural failure modes, including hallucination, sycophancy, reward hacking…