Evolutionary neural architecture design for multivariate time-series forecasting remains under-explored, with most approaches relying on fixed Transformer architectures despite substantial variation across tasks and forecasting settings. This paper introduces an evolutionary neural architecture search framework for discovering task-adaptive Transformer-like models for time-series forecasting (EvoTS). Architectures are encoded using a modular genome representation that enables flexible composition of attention, feedforward, and projection components, while a repair mechanism enforces structural validity throughout the evolutionary process. This formulation allows effective exploration of a diverse architecture space without relying on hand-crafted design rules.

High-performance computing (HPC) systems are difficult to use due to complex job scheduling, resource selection, and limited feedback on job failures. This paper presents Inkly, a data-driven HPC assistant with job intelligence that augments user workflows with insights derived from historical Slurm job data. Inkly ingests job records via sacct, stores them in a SQLite database, and computes aggregate metrics such as partition success rates, CPU and memory usage patterns, and failure distributions. These metrics are added to the prompts to guide users toward more effective job configurations. The system enforces safety through prompt filtering, command guardrails, and containerized execution using Apptainer.

Meta-algorithmics, the field of leveraging machine learning to use algorithms more efficiently, has achieved impressive performance improvements in many areas of AI. It treats the algorithms to improve on as black boxes – nothing is known about their inner workings. This allows meta-algorithmic techniques to be deployed in many applications, but leaves potential performance improvements untapped by ignoring information that the algorithms could provide. In this paper, we open the black box without sacrificing the universal applicability of meta-algorithmic techniques by automatically analyzing the source code of the algorithms under consideration and show how to use it to improve algorithm selection performance. We demonstrate improvements of up to 82% on the standard ASlib benchmark library.