There is a growing interest in leveraging multiple large language models (LLMs) for automated code optimization. However, industrial platforms deploying multiple LLMs face a critical challenge: prompts optimized for one LLM often fail with others, requiring expensive model-specific prompt engineering. This cross-model prompt engineering bottleneck severely limits the practical deployment of multi-LLM systems in production environments. We introduce Meta-Prompted Code Optimization (Mpco), a framework that automatically generates high-quality, task-specific prompts across diverse LLMs while maintaining industrial efficiency requirements. Mpco leverages meta-prompting to dynamically synthesize context-aware optimization prompts by integrating project metadata, task requirements, and LLM-specific contexts. It is an essential part of the ARTEMIS code optimization platform for automated validation and scaling.Our comprehensive evaluation on five real-world codebases with 366 hours of runtime benchmarking demonstrates Mpco’s effectiveness: it achieves overall performance improvements up to 19.06% with the best statistical rank across all systems compared to baseline methods. Analysis shows that 96% of the top-performing optimizations stem from meaningful edits. Through systematic ablation studies and meta-prompter sensitivity analysis, we identify that comprehensive context integration is essential for effective meta-prompting and that major LLMs can serve effectively as meta-prompters, providing actionable insights for industrial practitioners.

Increasing shape-bias in deep neural networks has been shown to improve robustness to common corruptions and noise. In this paper we analyze the adversarial robustness of texture and shape-biased models to Universal Adversarial Perturbations (UAPs). We use UAPs to evaluate the robustness of DNN models with varying degrees of shape-based training. We find that shape-biased models do not markedly improve adversarial robustness, and we show that ensembles of texture and shape-biased models can improve universal adversarial robustness while maintaining strong performance.

The k -nearest-neighbors ( k NN) graph is a popular and powerful data structure that is used in various areas of Data Science, but the high computational cost of obtaining it hinders its use on large datasets. Approximate solutions have been described in the literature using diverse techniques, among which Locality-sensitive Hashing (LSH) is a promising alternative that still has unsolved problems. We present Variable Resolution Locality-sensitive Hashing, an algorithm that addresses these problems to obtain an approximate k NN graph at a significantly reduced computational cost. Its usability is greatly enhanced by its capacity to automatically find adequate hyperparameter values, a common hindrance to LSH-based methods. Moreover, we provide an implementation in the distributed computing framework Apache Spark that takes advantage of the structure of the algorithm to efficiently distribute the computational load across multiple machines, enabling practitioners to apply this solution to very large datasets. Experimental results show that our method offers significant improvements over the state-of-the-art in the field and shows very good scalability as more machines are added to the computation.

Data structure selection and tuning is laborious but can vastly improve an application’s performance and memory footprint. Some data structures share a common interface and enjoy multiple implementations. We call them Darwinian Data Structures (DDS), since we can subject their implementations to survival of the fittest. We introduce ARTEMIS a multi-objective, cloud-based search-based optimisation framework that automatically finds optimal, tuned DDS modulo a test suite, then changes an application to use that DDS. ARTEMIS achieves substantial performance improvements for every project in 5 Java projects from DaCapo benchmark, 8 popular projects and 30 uniformly sampled projects from GitHub. For execution time, CPU usage, and memory consumption, ARTEMIS finds at least one solution that improves all measures for 86% (37/43) of the projects. The median improvement across the best solutions is 4.8%, 10.1%, 5.1% for runtime, memory and CPU usage.