Jul 2026· Proceedings of the Genetic and Evolutionary Computation Conference Companion· pp. 513-516· 0 citations· 7 references
TL;DR
Experiments on BBOB show the feedback loop yields mutation strategies that outperform classical DE operators and LLM-generated variants without feedback.
Abstract
We propose an LLM-driven framework to generate and iteratively refine Differential Evolution mutation operators via structured, performance-based feedback. Starting from standard DE strategies (e.g., DE/rand/*, DE/best/*, current-to-rand/1, JADE, Union DE), the LLM proposes new operators, evaluates them with quantitative indicators, and uses the best as a reference for the next refinement cycle; we also compare different LLMs. Experiments on BBOB (30D/40D, 30 runs) show the feedback loop yields mutation strategies that outperform classical DE operators and LLM-generated variants without feedback.
Analysis shows that many generated operators use semantics to guide selection, suggesting that LLMs can produce non-trivial search heuristics from the task description alone, and the relationship between public LLM leaderboard rankings and GP performance is examined.
Hengzhe Zhang, Qi Chen, Bing Xue et al.· 1 citation
This work introduces an Evolutionary Language Model that searches over natural-language policy descriptions and compiles typed programs for execution and shows that language can serve as a steerable, execution-grounded search representation over executable program space.
Matthew Siper, A. Khalifa, Julian Togelius· 0 citations
This work proposes a hybrid framework that integrates Large Language Models into GP in two complementary roles: as a semantic mutation operator that proposes non-local program rewrites during evolution, and as a post-evolution repair that iteratively refines single failed programs after search terminates.
Woletemaryam Liyew, Dojun Oh, Seokki Lee et al.· Proceedings of the Genetic a...· 0 citations
Evolutionary program search guided by Large Language Models (LLMs) has emerged as a powerful paradigm for automated scientific discovery. However, current approaches are fundamentally constrained by three bottlenecks: structurally blind parent selection, sparse whole-program evaluation rewards, and static mutation operators that fail to adapt during search. We present GAE (Graph-Augmented Evolution), a framework that resolves these limitations through a tightly coupled, three-pillar architecture. First, a relational graph neural network (GNN) parses programs into typed computation graphs, producing structure-aware embeddings. Second, an RL-optimized meta-controller leverages these embeddings to replace blind evolutionary sampling with a directed policy, dynamically selecting optimal parents and mutation directions based on reward history. Third, an online GRPO fine-tuning loop continuously updates the LLM mutation operator at test-time using group-normalized evaluation rewards, directly aligning the model's generation distribution with high-fitness structural edits. We evaluate GAE on a challenging scientific discovery task: symbolic regression for complex nonlinear oscillator systems. By transforming stochastic search into a directed, self-improving trajectory, GAE efficiently discovers closed-form physical equations, consistently matching or outperforming static LLM-driven baselines and achieving state-of-the-art out-of-distribution performance.
This work proposes a general LES framework that incorporates feature-assisted niche construction within abstract search spaces, enabling the seamless integration of niche-based search strategies from evolutionary computation and introduces PartEvo (Partition to Evolve), an LES method that combines niche collaborative search and advanced prompting strategies to improve algorithm discovery efficiency.
Qinglong Hu, Qingfu Zhang· Neural Information Processin...· 10 citations· ⚡3
We study zeroth-order post-training of language models by optimizing only LoRA adapter parameters with population-based black-box optimizers. Representing each candidate as a single LoRA weight vector with frozen base weights, we compare Differential Evolution (DE) and adaptive variants (JADE, SHADE), Particle Swarm Optimization (PSO), Grey Wolf Optimization (GWO), and Whale Optimization Algorithm (WOA) under a unified pipeline on the Countdown arithmetic task. To address clifflike fitness landscapes, we introduce a dense reward shaping function providing partial credit for structure, number usage, and numeric closeness. Across small models, these optimizers substantially improve reward and accuracy, with adaptive DE variants emerging as consistently strong performers.
M. Ulyanova, Fedor Buzaev, Andrei M. Ermakov· Proceedings of the Genetic a...· 0 citations