Large Language Model-Powered Evolutionary Code Optimization on a Phylogenetic Tree

• URL: http://arxiv.org/abs/2601.14523v1
• Date: Tue, 20 Jan 2026 22:32:52 GMT
• Title: Large Language Model-Powered Evolutionary Code Optimization on a Phylogenetic Tree
• Authors: Leyi Zhao, Weijie Huang, Yitong Guo, Jiang Bian, Chenghong Wang, Xuhong Zhang,
• Abstract summary: PhyloEvolve is a system that reframes GPU-oriented algorithm optimization as an In-Context Reinforcement Learning problem.<n>We introduce a phylogenetic tree representation that captures inheritance, divergence, and recombination among algorithm variants.<n>We evaluate PhyloEvolve on scientific computing workloads including PDE solvers, manifold learning, and spectral graph algorithms.
• Score: 17.08113692977552
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Optimizing scientific computing algorithms for modern GPUs is a labor-intensive and iterative process involving repeated code modification, benchmarking, and tuning across complex hardware and software stacks. Recent work has explored large language model (LLM)-assisted evolutionary methods for automated code optimization, but these approaches primarily rely on outcome-based selection and random mutation, underutilizing the rich trajectory information generated during iterative optimization. We propose PhyloEvolve, an LLM-agent system that reframes GPU-oriented algorithm optimization as an In-Context Reinforcement Learning (ICRL) problem. This formulation enables trajectory-conditioned reuse of optimization experience without model retraining. PhyloEvolve integrates Algorithm Distillation and prompt-based Decision Transformers into an iterative workflow, treating sequences of algorithm modifications and performance feedback as first-class learning signals. To organize optimization history, we introduce a phylogenetic tree representation that captures inheritance, divergence, and recombination among algorithm variants, enabling backtracking, cross-lineage transfer, and reproducibility. The system combines elite trajectory pooling, multi-island parallel exploration, and containerized execution to balance exploration and exploitation across heterogeneous hardware. We evaluate PhyloEvolve on scientific computing workloads including PDE solvers, manifold learning, and spectral graph algorithms, demonstrating consistent improvements in runtime, memory efficiency, and correctness over baseline and evolutionary methods. Code is published at: https://github.com/annihi1ation/phylo_evolve

Related papers

• AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization [61.535567824938205]
  We introduce AdaEvolve, a framework that reformulates LLM-driven evolution as a hierarchical adaptive optimization problem.<n>AdaEvolve consistently outperforms the open-ended baselines across 185 different open-ended optimization problems.
  arXiv  Detail & Related papers  (2026-02-23T18:45:31Z)
• Frankenstein Optimizer: Harnessing the Potential by Revisiting Optimization Tricks [2.932254642052481]
  We propose Frankenstein, which combines various adaptive algorithms' mechanisms.<n>Experiments on computer vision, natural language processing, few-shot learning, and scientific simulations show that Frankenstein surpasses existing adaptive algorithms and gradient descent (SGD)<n>This research deepens our understanding of adaptive algorithms through centered kernel alignment analysis and loss landscape visualization during the learning process.
  arXiv  Detail & Related papers  (2025-03-04T00:25:54Z)
• Evolution Transformer: In-Context Evolutionary Optimization [6.873777465945062]
  We introduce Evolution Transformer, a causal Transformer architecture, which can flexibly characterize a family of Evolution Strategies. We train the model weights using Evolutionary Algorithm Distillation, a technique for supervised optimization of sequence models. We analyze the resulting properties of the Evolution Transformer and propose a technique to fully self-referentially train the Evolution Transformer.
  arXiv  Detail & Related papers  (2024-03-05T14:04:13Z)
• Analyzing and Enhancing the Backward-Pass Convergence of Unrolled Optimization [50.38518771642365]
  The integration of constrained optimization models as components in deep networks has led to promising advances on many specialized learning tasks. A central challenge in this setting is backpropagation through the solution of an optimization problem, which often lacks a closed form. This paper provides theoretical insights into the backward pass of unrolled optimization, showing that it is equivalent to the solution of a linear system by a particular iterative method. A system called Folded Optimization is proposed to construct more efficient backpropagation rules from unrolled solver implementations.
  arXiv  Detail & Related papers  (2023-12-28T23:15:18Z)
• Efficient Inverse Design Optimization through Multi-fidelity Simulations, Machine Learning, and Search Space Reduction Strategies [0.8646443773218541]
  This paper introduces a methodology designed to augment the inverse design optimization process in scenarios constrained by limited compute. The proposed methodology is analyzed on two distinct engineering inverse design problems: airfoil inverse design and the scalar field reconstruction problem. Notably, this method is adaptable across any inverse design application, facilitating a synergy between a representative low-fidelity ML model, and high-fidelity simulation, and can be seamlessly applied across any variety of population-based optimization algorithms.
  arXiv  Detail & Related papers  (2023-12-06T18:20:46Z)
• Neuroevolution of Physics-Informed Neural Nets: Benchmark Problems and Comparative Results [25.12291688711645]
  Physics-informed neural networks (PINNs) are one of the key techniques at the forefront of recent advances. PINNs' unique loss formulations lead to a high degree of complexity and ruggedness that may not be conducive for gradient descent. Neuroevolution algorithms, with their superior global search capacity, may be a better choice for PINNs.
  arXiv  Detail & Related papers  (2022-12-15T05:54:16Z)
• An Empirical Evaluation of Zeroth-Order Optimization Methods on AI-driven Molecule Optimization [78.36413169647408]
  We study the effectiveness of various ZO optimization methods for optimizing molecular objectives. We show the advantages of ZO sign-based gradient descent (ZO-signGD) We demonstrate the potential effectiveness of ZO optimization methods on widely used benchmark tasks from the Guacamol suite.
  arXiv  Detail & Related papers  (2022-10-27T01:58:10Z)
• Data-driven evolutionary algorithm for oil reservoir well-placement and control optimization [3.012067935276772]
  Generalized data-driven evolutionary algorithm (GDDE) is proposed to reduce the number of simulation runs on well-placement and control optimization problems. Probabilistic neural network (PNN) is adopted as the classifier to select informative and promising candidates.
  arXiv  Detail & Related papers  (2022-06-07T09:07:49Z)
• Improving RNA Secondary Structure Design using Deep Reinforcement Learning [69.63971634605797]
  We propose a new benchmark of applying reinforcement learning to RNA sequence design, in which the objective function is defined to be the free energy in the sequence's secondary structure. We show results of the ablation analysis that we do for these algorithms, as well as graphs indicating the algorithm's performance across batches.
  arXiv  Detail & Related papers  (2021-11-05T02:54:06Z)
• Harnessing Heterogeneity: Learning from Decomposed Feedback in Bayesian Modeling [68.69431580852535]
  We introduce a novel GP regression to incorporate the subgroup feedback. Our modified regression has provably lower variance -- and thus a more accurate posterior -- compared to previous approaches. We execute our algorithm on two disparate social problems.
  arXiv  Detail & Related papers  (2021-07-07T03:57:22Z)
• EOS: a Parallel, Self-Adaptive, Multi-Population Evolutionary Algorithm for Constrained Global Optimization [68.8204255655161]
  EOS is a global optimization algorithm for constrained and unconstrained problems of real-valued variables. It implements a number of improvements to the well-known Differential Evolution (DE) algorithm. Results prove that EOSis capable of achieving increased performance compared to state-of-the-art single-population self-adaptive DE algorithms.
  arXiv  Detail & Related papers  (2020-07-09T10:19:22Z)
• Global Optimization of Gaussian processes [52.77024349608834]
  We propose a reduced-space formulation with trained Gaussian processes trained on few data points. The approach also leads to significantly smaller and computationally cheaper sub solver for lower bounding. In total, we reduce time convergence by orders of orders of the proposed method.
  arXiv  Detail & Related papers  (2020-05-21T20:59:11Z)
• Learning to be Global Optimizer [28.88646928299302]
  We learn an optimal network and escaping capability algorithm for some benchmark functions. We show that the learned algorithm significantly outperforms some well-known classical optimization algorithms.
  arXiv  Detail & Related papers  (2020-03-10T03:46:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.