Penetration testing, the simulation of cyberattacks to identify security vulnerabilities, presents a sequential decision-making problem well-suited for reinforcement learning (RL) automation. Like many applications of RL to real-world problems, partial observability presents a major challenge, as it invalidates the Markov property present in Markov Decision Processes (MDPs). Partially Observable MDPs require history aggregation or belief state estimation to learn successful policies. We investigate stochastic, partially observable penetration testing scenarios over host networks of varying size, aiming to better reflect real-world complexity through more challenging and representative benchmarks. This approach leads to the development of more robust and transferable policies, which are crucial for ensuring reliable performance across diverse and unpredictable real-world environments. Using vanilla Proximal Policy Optimization (PPO) as a baseline, we compare a selection of PPO variants designed to mitigate partial observability, including frame-stacking, augmenting observations with historical information, and employing recurrent or transformer-based architectures. We conduct a systematic empirical analysis of these algorithms across different host network sizes. We find that this task greatly benefits from history aggregation. Converging three times faster than other approaches. Manual inspection of the learned policies by the algorithms reveals clear distinctions and provides insights that go beyond quantitative results.

Abstract--Multi-stage sequential (MSS) robotic manipulation tasks are prevalent and crucial in robotics. They often involve state ambiguity, where visually similar observations correspond to different actions. We present SAGE, a state-aware guided imitation learning framework that models tasks as a Hidden Markov Decision Process (HMDP) to explicitly capture latent task stages and resolve ambiguity. We instantiate the HMDP with a state transition network that infers hidden states, and a state-aware action policy that conditions on both observations and hidden states to produce actions, thereby enabling disambiguation across task stages. T o reduce manual annotation effort, we propose a semi-automatic labeling pipeline combining active learning and soft label interpolation. In real-world experiments across multiple complex MSS tasks with state ambiguity, SAGE achieved 100% task success under the standard evaluation protocol, markedly surpassing the baselines. Ablation studies further show that such performance can be maintained with manual labeling for only about 13% of the states, indicating its strong effectiveness. OBOTIC manipulation tasks have attracted significant attention due to their broad applications. Vision-based strategies have been widely adopted [1], and have demonstrated remarkable performance across a variety of real-world scenarios [2], [3], [4], [5], [6]. However, a particular class of tasks--Multi-Stage Sequential (MSS) tasks--introduces distinctive challenges to vision-based policies. MSS tasks are characterized by a sequence of interdependent stages that must be executed in a prescribed temporal order, often requiring the policy to perform long-horizon reasoning, retain contextual information from prior steps, and ensure coherent progression across successive stages. In such cases, visually similar observations may correspond to different actions, resulting in ambiguity during action selection. An illustrative case is the Push Buttons task shown in Figure 1. The visual observations at stages 1-1, 2-1, and 3-1 are nearly indistinguishable; however, the correct action--pressing the yellow, pink, or blue button--requires knowledge of the current task stage to be correctly determined.

We introduce GuessingGame, a protocol for evaluating large language models (LLMs) as strategic question-askers in open-ended, open-domain settings. A Guesser LLM identifies a hidden object by posing free-form questions to an Oracle without predefined choices or candidate lists. To measure question quality, we propose two information gain (IG) metrics: a Bayesian method that tracks belief updates over semantic concepts using LLM-scored relevance, and an entropy-based method that filters candidates via ConceptNet. Both metrics are model-agnostic and support post hoc analysis. Across 858 games with multiple models and prompting strategies, higher IG strongly predicts efficiency: a one-standard-deviation IG increase reduces expected game length by 43\%. Prompting constraints guided by IG, such as enforcing question diversity, enable weaker models to significantly improve performance. These results show that question-asking in LLMs is both measurable and improvable, and crucial for interactive reasoning.

Multi-Agent Reinforcement Learning (MARL) is a growing research area which gained significant traction in recent years, extending Deep RL applications to a much wider range of problems. A particularly challenging class of problems in this domain is Heterogeneous Multi-Agent Reinforcement Learning (HeMARL), where agents with different sensors, resources, or capabilities must cooperate based on local information. The large number of real-world situations involving heterogeneous agents makes it an attractive research area, yet underexplored, as most MARL research focuses on homogeneous agents (e.g., a swarm of identical robots). In MARL and single-agent RL, standardized environments such as ALE and SMAC have allowed to establish recognized benchmarks to measure progress. However, there is a clear lack of such standardized testbed for cooperative HeMARL. As a result, new research in this field often uses simple environments, where most algorithms perform near optimally, or uses weakly heterogeneous MARL environments.

This study examines credit default prediction by comparing three techniques, namely SMOTE, SMOTE-Tomek, and ADASYN, that are commonly used to address the class imbalance problem in credit default situations. Recognizing that credit default datasets are typically skewed, with defaulters comprising a much smaller proportion than non-defaulters, we began our analysis by evaluating machine learning (ML) models on the imbalanced data without any resampling to establish baseline performance. These baseline results provide a reference point for understanding the impact of subsequent balancing methods. In addition to traditional classifiers such as Naive Bayes and K-Nearest Neighbors (KNN), our study also explores the suitability of advanced ensemble boosting algorithms, including Extreme Gradient Boosting (XGBoost), AdaBoost, Gradient Boosting Machines (GBM), and Light GBM for credit default prediction using Boruta feature selection and DBSCAN-based outlier detection, both before and after resampling. A real-world credit default data set sourced from the University of Cleveland ML Repository was used to build ML classifiers, and their performances were tested. The criteria chosen to measure model performance are the area under the receiver operating characteristic curve (ROC-AUC), area under the precision-recall curve (PR-AUC), G-mean, and F1-scores. The results from this empirical study indicate that the Boruta+DBSCAN+SMOTE-Tomek+GBM classifier outperformed the other ML models (F1-score: 82.56%, G-mean: 82.98%, ROC-AUC: 90.90%, PR-AUC: 91.85%) in a credit default context. The findings establish a foundation for future progress in creating more resilient and adaptive credit default systems, which will be essential as credit-based transactions continue to rise worldwide.

This research investigates how Machine Learning (ML) algorithms can assist in workload allocation strategies by detecting tasks with node affinity operators (referred to as constraint operators), which constrain their execution to a limited number of nodes. Using real-world Google Cluster Data (GCD) workload traces and the AGOCS framework, the study extracts node attributes and task constraints, then analyses them to identify suitable node-task pairings. It focuses on tasks that can be executed on either a single node or fewer than a thousand out of 12.5k nodes in the analysed GCD cluster. Task constraint operators are compacted, pre-processed with one-hot encoding, and used as features in a training dataset. Various ML classifiers, including Artificial Neural Networks, K-Nearest Neighbours, Decision Trees, Naive Bayes, Ridge Regression, Adaptive Boosting, and Bagging, are fine-tuned and assessed for accuracy and F1-scores. The final ensemble voting classifier model achieved 98% accuracy and a 1.5-1.8% misclassification rate for tasks with a single suitable node.

The spreading dynamics in social networks are often studied under the assumption that individuals' statuses, whether informed or infected, are fully observable. However, in many real-world situations, such statuses remain unobservable, which is crucial for determining an individual's potential to further spread the infection. While final statuses are hidden, intermediate indicators such as symptoms of infection are observable and provide useful representations of the underlying diffusion process. We propose a partial observability-aware Machine Learning framework to learn the characteristics of the spreading model. We term the method Distribution Classification, which utilizes the power of classifiers to infer the underlying transmission dynamics. Through extensive benchmarking against Approximate Bayesian Computation and GNN-based baselines, our framework consistently outperforms these state-of-the-art methods, delivering accurate parameter estimates across diverse diffusion settings while scaling efficiently to large networks. We validate the method on synthetic networks and extend the study to a real-world insider trading network, demonstrating its effectiveness in analyzing spreading phenomena where direct observation of individual statuses is not possible.

This paper studies how insurers can chose which claims to investigate for fraud. Given a prediction model, typically only claims with the highest predicted propability of being fraudulent are investigated. We argue that this can lead to inconsistent learning and propose a randomized alternative. More generally, we draw a parallel with the multi-arm bandit literature and argue that, in the presence of selection, the obtained observations are not iid. Hence, dependence on past observations should be accounted for when updating parameter estimates. We formalize selection in a binary regression framework and show that model updating and maximum-likelihood estimation can be implemented as if claims were investigated at random. Then, we define consistency of selection strategies and conjecture sufficient conditions for consistency. Our simulations suggest that the often-used selection strategy can be inconsistent while the proposed randomized alternative is consistent. Finally, we compare our randomized selection strategy with Thompson sampling, a standard multi-arm bandit heuristic. Our simulations suggest that the latter can be inefficient in learning low fraud probabilities.

Large, sparse linear systems are pervasive in modern science and engineering, and Krylov subspace solvers are an established means of solving them. Yet convergence can be slow for ill-conditioned matrices, so practical deployments usually require preconditioners. Markov chain Monte Carlo (MCMC)-based matrix inversion can generate such preconditioners and accelerate Krylov iterations, but its effectiveness depends on parameters whose optima vary across matrices; manual or grid search is costly. We present an AI-driven framework recommending MCMC parameters for a given linear system. A graph neural surrogate predicts preconditioning speed from $A$ and MCMC parameters. A Bayesian acquisition function then chooses the parameter sets most likely to minimise iterations. On a previously unseen ill-conditioned system, the framework achieves better preconditioning with 50\% of the search budget of conventional methods, yielding about a 10\% reduction in iterations to convergence. These results suggest a route for incorporating MCMC-based preconditioners into large-scale systems.