Real-time operational dispatch in decentralized energy systems (DES) is critical for multi-sector integration. Rule-based strategies widely used in practice often exhibit suboptimal performance, and model-based optimization methods such as model predictive control (MPC) are constrained by heavy online computational demands and forecast reliance. To overcome these limitations, reinforcement learning (RL) has emerged as a promising data-driven alternative, allowing agents to learn adaptive control policies through direct environment interaction. Within the RL domain, this paper systematically compares two prominent paradigms: the neuroevolutionary approach (NEAT), which optimizes both network topologies and parameters but incurs high computational training costs, and the actor-critic method (SAC), which leverages off-policy transition data for superior sample efficiency.The comparison addresses three major points: dispatch quality on annual hourly load profiles, training and sample efficiency, and the influence of environment design on stable learning. In terms of dispatch quality, SAC achieves an operating-cost deviation of 7.10% from deterministic optimal dispatch, outperforming NEAT (7.42%) and the rule-based baselines (13.43% and 8.36%), while remaining above MPC (1.49%). In terms of single-run training effort, SAC requires 9.2 CPU-hours compared with 6048 CPU-hours for NEAT, although this figure excludes the one-time hyperparameter search overhead. Due to its high sensitivity to hyperparameters, identifying the optimal SAC configuration required 371 hyperparameter optimization trials, corresponding to approximately 3413 CPU-hours. This initial one-time investment is essential for gradient-based agents, while the resulting policies offer efficient real-time dispatch capabilities. Methodologically, the results show that dense per-step rewards, physics-informed fallback rules, repeated simulation for cycling constraints, and contextual markers for typical periods are key prerequisites for stable gradient-based learning. These findings position SAC as a promising method for the dispatch of decentralized energy systems while clarifying the modeling and tuning assumptions required for deployment.

Offline goal-conditioned reinforcement learning (GCRL) is typically benchmarked by the best tuned success rate of each method. This score measures attainable performance, but it does not reveal how reliably a learned goal-conditioned signal can be extracted into a policy: a method could succeed across many value-learning and extraction settings, or only at a narrow, hard-to-find configuration. We study this gap across four methods, GCIQL, GCIVL, QRL, and CRL, under a shared advantage-weighted regression (AWR) extractor. For each method, we construct trainability landscapes over the optimizer learning rate, which affects value learning and actor optimization, and AWR temperature, which controls how selectively the actor imitates high-advantage transitions. Across AntMaze, Cube, and Scene, we observe distinct regimes: high-scoring methods may be broadly accessible or brittle, while broad relative basins may still sit below low absolute ceilings. To interpret these differences, we pair landscapes with post-hoc diagnostics of future-vs-random goal discrimination and AWR weight concentration. Their relationship to downstream success is task-dependent. On AntMaze, where future goals align with path-like progress, these diagnostics explain landscape regimes. On Cube and Scene, goal ranking and manipulation control decouple: methods can rank goals well while failing downstream, or succeed through action-conditioned advantages despite weak future-vs-random separation. These results show that peak tuned success alone does not establish broadly extractable goal-conditioned behavior. Trainability landscapes expose this gap, while extraction diagnostics offer a lower-cost lens on how learned signals become policies.

Deep Reinforcement Learning (RL) agents often learn policies that achieve the same episodic return yet behave very differently, due to a combination of environmental (random transitions, initial conditions, reward noise) and algorithmic (minibatch selection, exploration noise) factors. In continuous control tasks, even small parameter shifts can produce unstable gaits, complicating both algorithm comparison and real-world transfer. Previous work has shown that such instability arises when policy updates traverse noisy neighborhoods and that the spread of post-update return distribution R(θ), obtained by repeatedly sampling minibatches, updating θ, and measuring final returns, is a useful indicator of this noise. Although explicitly constraining the policy to maintain a narrow R(θ) can improve stability, directly estimating R(θ) is computationally expensive in high-dimensional settings. We propose an alternative that takes advantage of environmental stochasticity to mitigate update-induced variability. Specifically, we model state-action return distribution through a distributional critic and then bias the advantage function of PPO using higher-order moments (skewness and kurtosis) of this distribution. By penalizing extreme tail behaviors, our method discourages policies from entering parameter regimes prone to instability. We hypothesize that in environments where post-update critic values align poorly with post-update returns, standard PPO struggles to produce a narrow R(θ). In such cases, our moment-based correction narrows R(θ), improving stability by up to 75

Automated algorithm configuration aims at finding well-performing parameter configurations for a given problem, and it has proven to be effective within many AI domains, including evolutionary computation. Initially, the focus was on excelling in one performance objective, but, in reality, most tasks have a variety of (conflicting) objectives. The surging demand for trustworthy and resource-efficient AI systems makes this multiobjective perspective even more prevalent. We propose a new general-purpose multiobjective automated algorithm configurator by extending the widely-used SMAC framework. Instead of finding a single configuration, we search for a nondominated set that approximates the actual Pareto set. We propose a pure multiobjective Bayesian optimization approach for obtaining promising configurations by using the predicted hypervolume improvement as acquisition function. We also present a novel intensification procedure to efficiently handle the selection of configurations in a multiobjective context. Our approach is empirically validated and compared across various configuration scenarios in four AI domains, demonstrating superiority over baseline methods, competitiveness with MO-ParamILS on individual scenarios, and an overall best performance.

LLM agents in interactive environments are highly sensitive to their prompts, yet prompt engineering remains a manual, task-specific process. We introduce an automated prompt optimization framework for LLM agents that decomposes the observation-to-action pipeline into a goal-conditioned descriptor agent and an action selection agent, and iteratively refines each module's prompt through an LLM-driven evolutionary loop guided by environment returns. We propose a behavior analyzer to attribute episode outcomes to specific prompt components, and a mutator to propose targeted revisions to the prompt, before validating them through environment rollouts. We evaluate on all five BabyAI tasks in the BALROG benchmark, comparing our pipeline against BALROG's RobustCoTAgent under both plain and guided prompt initializations. Optimization improves performance consistently across tasks and conditions, without requiring updates to the model weights. On PutNext, a multi-step coordination task where the RobustCoTAgent achieves 0% success, our framework reaches up to 72.5% success rate using the same underlying LLM with optimized prompts. These results suggest that a multi-agent framework, combined with automatic prompt optimization, enhances LLMs without the need for fine-tuning or extensive human supervision.

Reinforcement learning (RL) has shown remarkable success across a wide range of complex tasks. However, RL outcomes can be highly stochastic, and both expected performance and variability often depend on hyperparameter (HP) configurations. We propose efficient and risk-averse heteroscedastic Bayesian Optimization (ERAHBO), a Bayesian optimization method that models both the mean and variance of learning outcomes as functions of the HP configurations. ERAHBO aims to identify HP configurations that achieve high average return while reducing variability across training runs, and it improves the sample efficiency of the HP optimization via adaptive re-sampling rather than a fixed budget per HP. Empirical evaluations across diverse RL algorithms and environments demonstrate that ERAHBO generally outperforms both risk-neutral and risk-averse baselines, delivering improved sample efficiency for risk-averse returns.

Inverse design, particularly geometric shape optimization, provides a systematic approach for developing high-performance nanophotonic devices. While numerous optimization algorithms exist, previous global approaches exhibit slow convergence and conversely local search strategies frequently become trapped in local optima. To address the limitations inherent to both local and global approaches, we introduce BONNI: Bayesian optimization through neural network ensemble surrogates with interior point optimization. It augments global optimization with an efficient incorporation of gradient information to determine optimal sampling points. This capability allows BONNI to circumvent the local optima found in many nanophotonic applications, while capitalizing on the efficiency of gradient-based optimization. We demonstrate BONNI's capabilities in the design of a distributed Bragg reflector as well as a dual-layer grating coupler through an exhaustive comparison against other optimization algorithms commonly used in literature. Using BONNI, we were able to design a 10-layer distributed Bragg reflector with only 4.5

Choosing a suitable ML model is a complex task that can depend on several objectives, e.g., accuracy, model size, fairness, inference time, or energy consumption. In practice, this requires trading off multiple, often competing, objectives through multi-objective optimization (MOO). However, existing MOO methods typically treat all hyperparameters as equally important, overlooking that hyperparameter importance (HPI) can vary significantly depending on the trade-off between objectives. We propose a novel dynamic optimization approach that prioritizes the most influential hyperparameters based on varying objective trade-offs during the search process, which accelerates empirical convergence and leads to better solutions. Building on prior work on HPI for MOO post-analysis, we now integrate HPI, calculated with HyperSHAP, into the optimization. For this, we leverage the objective weightings naturally produced by the MOO algorithm ParEGO and adapt the configuration space by fixing the unimportant hyperparameters, allowing the search to focus on the important ones. Eventually, we validate our method with diverse tasks from PyMOO and YAHPO-Gym. Empirical results demonstrate improvements in convergence speed and Pareto front quality compared to baselines.

Spatial accelerators, composed of arrays of compute-memory integrated units, offer an attractive platform for deploying inference workloads with low latency and low energy consumption. However, fully exploiting their architectural advantages typically requires careful, expert-driven mapping of computational graphs to distributed processing elements. In this work, we automate this process by framing the mapping challenge as a black-box optimization problem. We introduce the first evolutionary, hardware-in-the-loop mapping framework for neuromorphic accelerators, enabling users without deep hardware knowledge to deploy workloads more efficiently. We evaluate our approach on Intel Loihi 2, a representative spatial accelerator featuring 152 cores per chip in a 2D mesh. Our method achieves up to 35% reduction in total latency compared to default heuristics on two sparse multi-layer perceptron networks. Furthermore, we demonstrate the scalability of our approach to multi-chip systems and observe an up to 40% improvement in energy efficiency, without explicitly optimizing for it.

Large-scale hyperparameter optimization (HPO) in automated machine learning (AutoML) consumes substantial computational resources, raising growing concerns about scalability and energy efficiency. Existing methods use prior information heuristically to accelerate both black-box and multi-fidelity settings, but they lack a characterization of how prior informativeness quantitatively reduces sample complexity. In this work, we provide the first distribution-dependent sample complexity bounds for multi-fidelity HPO with priors through the formal lens of fixed-budget best-arm identification. By modeling priors directly over arm means as configuration performance, we derive explicit, distribution-dependent error bounds that quantify the relationship between priors and evaluation budget. Our analysis shows that informative priors, which concentrate probability mass on near-optimal arms, yield reductions in the number of required evaluations, whereas baseline performance is recovered with uninformative or misleading priors. We conduct proof-of-concept experiments on a synthetic benchmark and on LCBench, a common multi-fidelity HPO benchmark for deep learning, to confirm our theoretical results, achieving up to 90

Hyperparameter optimization (HPO) is a crucial step in achieving strong predictive performance. Yet, the impact of individual hyperparameters on model generalization is highly context-dependent, prohibiting a one-size-fits-all solution and requiring opaque HPO methods to find optimal configurations. However, the black-box nature of most HPO methods undermines user trust and discourages adoption. To address this, we propose a game-theoretic explainability framework for HPO based on Shapley values and interactions. Our approach provides an additive decomposition of a performance measure across hyperparameters, enabling local and global explanations of hyperparameters' contributions and their interactions. The framework, named HyperSHAP, offers insights into ablation studies, the tunability of learning algorithms, and optimizer behavior across different hyperparameter spaces. We demonstrate HyperSHAP's capabilities on various HPO benchmarks to analyze the interaction structure of the corresponding HPO problems, demonstrating its broad applicability and actionable insights for improving HPO.

Inverse design provides a systematic approach for developing high-performance nanophotonic devices. Although numerous optimization algorithms exist, previous global approaches exhibit slow convergence, and conversely, local search strategies frequently become trapped in local optima. To address the limitations inherent to both, we introduce BONNI: Bayesian optimization through neural network ensemble surrogates with interior point optimization. It augments global optimization by efficiently incorporating gradient information to determine optimal sampling points. We demonstrate BONNI's capabilities in the design of a distributed Bragg reflector and dual-layer grating coupler through a comparison with other commonly used optimization algorithms.

The quadratic computational complexity of softmax transformers has become a bottleneck in long-context scenarios. In contrast, linear attention model families provide a promising direction towards a more efficient sequential model. These linear attention models compress past KV values into a single hidden state, thereby efficiently reducing complexity during both training and inference. However, their expressivity remains limited by the size of their hidden state. Previous work proposed interleaving softmax and linear attention layers to reduce computational complexity while preserving expressivity. Nevertheless, the efficiency of these models remains bottlenecked by their softmax attention layers. In this paper, we propose Neural Attention Search Linear (NAtS-L), a framework that applies both linear attention and softmax attention operations within the same layer on different tokens. NAtS-L automatically determines whether a token can be handled by a linear attention model, i.e., tokens that have only short-term impact and can be encoded into fixed-size hidden states, or require softmax attention, i.e., tokens that contain information related to long-term retrieval and need to be preserved for future queries. By searching for optimal Gated DeltaNet and softmax attention combinations across tokens, we show that NAtS-L provides a strong yet efficient token-level hybrid architecture.

Medical Image Segmentation (MIS) includes diverse tasks, from bone to organ segmentation, each with its own challenges in finding the best segmentation model. The state-of-the-art AutoML-related MIS-framework nnU-Net automates many aspects of model configuration but remains constrained by fixed hyperparameters and heuristic design choices. As a full-AutoML framework for MIS, we propose Auto-nnU-Net, a novel nnU-Net variant enabling hyperparameter optimization (HPO), neural architecture search (NAS), and hierarchical NAS (HNAS). Additionally, we propose Regularized PriorBand to balance model accuracy with the computational resources required for training, addressing the resource constraints often faced in real-world medical settings that limit the feasibility of extensive training procedures. We evaluate our approach across diverse MIS datasets from the well-established Medical Segmentation Decathlon, analyzing the impact of AutoML techniques on segmentation performance, computational efficiency, and model design choices. The results demonstrate that our AutoML approach substantially improves the segmentation performance of nnU-Net on 6 out of 10 datasets and is on par on the other datasets while maintaining practical resource requirements. Our code is available at https://github.com/automl/AutoNNUnet.

Programmatic hyperparameter optimization (HPO) methods, such as Bayesian optimization and evolutionary algorithms, are known for their sample efficiency in identifying optimal configurations for machine learning (ML) models. However, practitioners often use less efficient methods, such as grid search, potentially resulting in under-optimized models. This discrepancy suggests that HPO method selection may be influenced by practitioner-specific motives, which remain insufficiently understood hindering user-centered advancement of HPO tools. To uncover these motives, we conducted 20 semi-structured interviews and an online survey with 49 ML practitioners. We revealed six primary goals (e.g., increasing ML model understanding) and 14 contextual factors (e.g., available computational resources) that influence practitioners' choices of HPO methods. This study provides a conceptual foundation for understanding real-world HPO practices and informs the development of more user-centered and context-adaptive HPO tools in automated ML (AutoML).

Addressing sensor drift is essential in industrial measurement systems, where precise data output is necessary for maintaining accuracy and reliability in monitoring processes, as it progressively degrades the performance of machine learning models over time. Our findings indicate that the standard cross-validation method used in existing model training overestimates performance by inadequately accounting for drift. This is primarily because typical cross-validation techniques allow data instances to appear in both training and testing sets, thereby distorting the accuracy of the predictive evaluation. As a result, these models are unable to precisely predict future drift effects, compromising their ability to generalize and adapt to evolving data conditions. This paper presents two solutions: (1) a novel sensor drift compensation learning paradigm for validating models, and (2) automated machine learning (AutoML) techniques to enhance classification performance and compensate sensor drift. By employing strategies such as data balancing, meta-learning, automated ensemble learning, hyperparameter optimization, feature selection, and boosting, our AutoML-DC (Drift Compensation) model significantly improves classification performance against sensor drift. AutoML-DC further adapts effectively to varying drift severities.

Hyperparameter Optimization (HPO) is crucial to develop well-performing machine learning models. In order to ease prototyping and benchmarking of HPO methods, we propose carps, a benchmark framework for Comprehensive Automated Research Performance Studies allowing to evaluate N optimizers on M benchmark tasks. In this first release of carps, we focus on the four most important types of HPO task types: blackbox, multi-fidelity, multi-objective and multi-fidelity-multi-objective. With 3 336 tasks from 5 community benchmark collections and 28 variants of 9 optimizer families, we offer the biggest go-to library to date to evaluate and compare HPO methods. The carps framework relies on a purpose-built, lightweight interface, gluing together optimizers and benchmark tasks. It also features an analysis pipeline, facilitating the evaluation of optimizers on benchmarks. However, navigating a huge number of tasks while developing and comparing methods can be computationally infeasible. To address this, we obtain a subset of representative tasks by minimizing the star discrepancy of the subset, in the space spanned by the full set. As a result, we propose an initial subset of 10 to 30 diverse tasks for each task type, and include functionality to re-compute subsets as more benchmarks become available, enabling efficient evaluations. We also establish a first set of baseline results on these tasks as a measure for future comparisons. With carps (https://www.github.com/automl/CARP-S), we make an important step in the standardization of HPO evaluation.

Hyperparameter optimization (HPO), as a central paradigm of AutoML, is crucial for leveraging the full potential of machine learning (ML) models; yet its complexity poses challenges in understanding and debugging the optimization process. We present DeepCAVE, a tool for interactive visualization and analysis, providing insights into HPO. Through an interactive dashboard, researchers, data scientists, and ML engineers can explore various aspects of the HPO process and identify issues, untouched potentials, and new insights about the ML model being tuned. By empowering users with actionable insights, DeepCAVE contributes to the interpretability of HPO and ML on a design level and aims to foster the development of more robust and efficient methodologies in the future.