Markov Decision Processes (MDPs) are the most common model for decision making under uncertainty in the Machine Learning community. An MDP captures non-determinism, probabilistic uncertainty, and an explicit model of action. A Reinforcement Learning (RL) agent learns to act in an MDP by maximizing a utility function. This paper considers the problem of learning a decision policy that maximizes utility subject to satisfying a constraint expressed in deontic logic. In this setup, the utility captures the agent's mission - such as going quickly from A to B. The deontic formula represents (ethical, social, situational) constraints on how the agent might achieve its mission by prohibiting classes of behaviors. We use the logic of Expected Act Utilitarianism, a probabilistic stit logic that can be interpreted over controlled MDPs. We develop a variation on policy improvement, and show that it reaches a constrained local maximum of the mission utility. Given that in stit logic, an agent's duty is derived from value maximization, this can be seen as a way of acting to simultaneously maximize two value functions, one of which is implicit, in a bi-level structure. We illustrate these results with experiments on sample MDPs.

Machine Learning (ML) models are increasingly integrated into safety-critical systems, such as autonomous vehicle platooning, to enable real-time decision-making. However, their inherent imperfection introduces a new class of failure: reasoning failures often triggered by distributional shifts between operational and training data. Traditional safety assessment methods, which rely on design artefacts or code, are ill-suited for ML components that learn behaviour from data. SafeML was recently proposed to dynamically detect such shifts and assign confidence levels to the reasoning of ML-based components. Building on this, we introduce a probabilistic safety assurance framework that integrates SafeML with Bayesian Networks (BNs) to model ML failures as part of a broader causal safety analysis. This allows for dynamic safety evaluation and system adaptation under uncertainty. We demonstrate the approach on an simulated automotive platooning system with traffic sign recognition.

Recent progress in Language Models (LMs) has dramatically advanced the field of natural language processing (NLP), excelling at tasks like text generation, summarization, and question answering. However, their inference remains computationally expensive and energy intensive, especially in settings with limited hardware, power, or bandwidth. This makes it difficult to deploy LMs in mobile, edge, or cost sensitive environments. To address these challenges, recent approaches have introduced multi LLM intelligent model selection strategies that dynamically allocate computational resources based on query complexity -- using lightweight models for simpler queries and escalating to larger models only when necessary. This survey explores two complementary strategies for efficient LLM inference: (i) routing, which selects the most suitable model based on the query, and (ii) cascading or hierarchical inference (HI), which escalates queries through a sequence of models until a confident response is found. Both approaches aim to reduce computation by using lightweight models for simpler tasks while offloading only when needed. We provide a comparative analysis of these techniques across key performance metrics, discuss benchmarking efforts, and outline open challenges. Finally, we outline future research directions to enable faster response times, adaptive model selection based on task complexity, and scalable deployment across heterogeneous environments, making LLM based systems more efficient and accessible for real world applications.

Multi-agent reinforcement learning (MARL) methods have achieved state-of-the-art results on a range of multi-agent tasks. Yet, MARL algorithms typically require significantly more environment interactions than their single-agent counterparts to converge, a problem exacerbated by the difficulty in exploring over a large joint action space and the high variance intrinsic to MARL environments. To tackle these issues, we propose a novel algorithm that combines a decomposed centralized critic with decentralized ensemble learning, incorporating several key contributions. The main component in our scheme is a selective exploration method that leverages ensemble kurtosis. We extend the global decomposed critic with a diversity-regularized ensemble of individual critics and utilize its excess kurtosis to guide exploration toward high-uncertainty states and actions. To improve sample efficiency, we train the centralized critic with a novel truncated variation of the TD($λ$) algorithm, enabling efficient off-policy learning with reduced variance. On the actor side, our suggested algorithm adapts the mixed samples approach to MARL, mixing on-policy and off-policy loss functions for training the actors. This approach balances between stability and efficiency and outperforms purely off-policy learning. The evaluation shows our method outperforms state-of-the-art baselines on standard MARL benchmarks, including a variety of SMAC II maps.

Large language models (LLMs)-empowered web agents enables automating complex, real-time web navigation tasks in enterprise environments. However, existing web agents relying on supervised fine-tuning (SFT) often struggle with generalization and robustness due to insufficient reasoning capabilities when handling the inherently dynamic nature of web interactions. In this study, we introduce WorkForceAgent-R1, an LLM-based web agent trained using a rule-based R1-style reinforcement learning framework designed explicitly to enhance single-step reasoning and planning for business-oriented web navigation tasks. We employ a structured reward function that evaluates both adherence to output formats and correctness of actions, enabling WorkForceAgent-R1 to implicitly learn robust intermediate reasoning without explicit annotations or extensive expert demonstrations. Extensive experiments on the WorkArena benchmark demonstrate that WorkForceAgent-R1 substantially outperforms SFT baselines by 10.26-16.59%, achieving competitive performance relative to proprietary LLM-based agents (gpt-4o) in workplace-oriented web navigation tasks.

Linear diffusion processes serve as canonical continuous-time models for dynamic decision-making under uncertainty. These systems evolve according to drift matrices that specify the instantaneous rates of change in the expected system state, while also experiencing continuous random disturbances modeled by Brownian noise. For instance, in medical applications such as artificial pancreas systems, the drift matrices represent the internal dynamics of glucose concentrations. Classical results in stochastic control provide optimal policies under perfect knowledge of the drift matrices. However, practical decision-making scenarios typically feature uncertainty about the drift; in medical contexts, such parameters are patient-specific and unknown, requiring adaptive policies for efficiently learning the drift matrices while ensuring system stability and optimal performance. We study the Thompson sampling (TS) algorithm for decision-making in linear diffusion processes with unknown drift matrices. For this algorithm that designs control policies as if samples from a posterior belief about the parameters fully coincide with the unknown truth, we establish efficiency. That is, Thompson sampling learns optimal control actions fast, incurring only a square-root of time regret, and also learns to stabilize the system in a short time period. To our knowledge, this is the first such result for TS in a diffusion process control problem. Moreover, our empirical simulations in three settings that involve blood-glucose and flight control demonstrate that TS significantly improves regret, compared to the state-of-the-art algorithms, suggesting it explores in a more guarded fashion. Our theoretical analysis includes characterization of a certain optimality manifold that relates the geometry of the drift matrices to the optimal control of the diffusion process, among others.

Recent advances have established the identifiability of a directed acyclic graph (DAG) under additive noise models (ANMs), spurring the development of various causal discovery methods. However, most existing methods make restrictive model assumptions, rely heavily on general independence tests, or require substantial computational time. To address these limitations, we propose a sequential procedure to orient undirected edges in a completed partial DAG (CPDAG), representing an equivalence class of DAGs, by leveraging the pairwise additive noise model (PANM) to identify their causal directions. We prove that this procedure can recover the true causal DAG assuming a restricted ANM. Building on this result, we develop a novel constraint-based algorithm for learning causal DAGs under nonlinear ANMs. Given an estimated CPDAG, we develop a ranking procedure that sorts undirected edges by their adherence to the PANM, which defines an evaluation order of the edges. To determine the edge direction, we devise a statistical test that compares the log-likelihood values, evaluated with respect to the competing directions, of a sub-graph comprising just the candidate nodes and their identified parents in the partial DAG. We further establish the structural learning consistency of our algorithm in the large-sample limit. Extensive experiments on synthetic and real-world datasets demonstrate that our method is computationally efficient, robust to model misspecification, and consistently outperforms many existing nonlinear DAG learning methods.

We consider the problem of sampling from a probability distribution $π$. It is well known that this can be written as an optimisation problem over the space of probability distribution in which we aim to minimise the Kullback--Leibler divergence from $π$. We consider several partial differential equations (PDEs) whose solution is a minimiser of the Kullback--Leibler divergence from $π$ and connect them to well-known Monte Carlo algorithms. We focus in particular on PDEs obtained by considering the Wasserstein--Fisher--Rao geometry over the space of probabilities and show that these lead to a natural implementation using importance sampling and sequential Monte Carlo. We propose a novel algorithm to approximate the Wasserstein--Fisher--Rao flow of the Kullback--Leibler divergence which empirically outperforms the current state-of-the-art. We study tempered versions of these PDEs obtained by replacing the target distribution with a geometric mixture of initial and target distribution and show that these do not lead to a convergence speed up.

Self-attention has emerged as a core component of modern neural architectures, yet its theoretical underpinnings remain elusive. In this paper, we study self-attention through the lens of interacting entities, ranging from agents in multi-agent reinforcement learning to alleles in genetic sequences, and show that a single layer linear self-attention can efficiently represent, learn, and generalize functions capturing pairwise interactions, including out-of-distribution scenarios. Our analysis reveals that self-attention acts as a mutual interaction learner under minimal assumptions on the diversity of interaction patterns observed during training, thereby encompassing a wide variety of real-world domains. In addition, we validate our theoretical insights through experiments demonstrating that self-attention learns interaction functions and generalizes across both population distributions and out-of-distribution scenarios. Building on our theories, we introduce HyperFeatureAttention, a novel neural network module designed to learn couplings of different feature-level interactions between entities. Furthermore, we propose HyperAttention, a new module that extends beyond pairwise interactions to capture multi-entity dependencies, such as three-way, four-way, or general n-way interactions.

We introduce an approach to topic modelling with document-level covariates that remains tractable in the face of large text corpora. This is achieved by de-emphasizing the role of parameter estimation in an underlying probabilistic model, assuming instead that the data come from a fixed but unknown distribution whose statistical functionals are of interest. We propose combining a convex formulation of non-negative matrix factorization with standard regression techniques as a fast-to-compute and useful estimate of such a functional. Uncertainty quantification can then be achieved by reposing non-parametric resampling methods on top of this scheme. This is in contrast to popular topic modelling paradigms, which posit a complex and often hard-to-fit generative model of the data. We argue that the simple, non-parametric approach advocated here is faster, more interpretable, and enjoys better inferential justification than said generative models. Finally, our methods are demonstrated with an application analysing covariate effects on discourse of flavours attributed to Canadian beers.