Safe Reinforcement Learning (RL) is crucial for achieving high performance while ensuring safety in real-world applications. However, the complex interplay of multiple uncertainty sources in real environments poses significant challenges for interpretable risk assessment and robust decision-making. To address these challenges, we propose Fuz-RL, a fuzzy measure-guided robust framework for safe RL. Specifically, our framework develops a novel fuzzy Bellman operator for estimating robust value functions using Choquet integrals. Theoretically, we prove that solving the Fuz-RL problem (in Constrained Markov Decision Process (CMDP) form) is equivalent to solving distributionally robust safe RL problems (in robust CMDP form), effectively reformulating the min-max optimization problem into a tractable CMDP with Choquet-integrated value functions. Empirical analyses on safe-control-gym and safety-gymnasium scenarios demonstrate that Fuz-RL effectively integrates with existing safe RL baselines in a model-free manner, significantly improving both safety and control performance under various types of uncertainties in observation, action, and dynamics. The code is available in https://github.com/waunx/FuzRL.

First, note that we shall use the same MDPs defined in Appendix D.1 as follows

This paper investigates model robustness in reinforcement learning (RL) via the framework of distributionally robust Markov decision processes (RMDPs). Despite recent efforts, the sample complexity of RMDPs is much less understood regardless of the uncertainty set in use; in particular, there exist large gaps between existing upper and lower bounds, and it is unclear if distributional robustness bears any statistical implications when benchmarked against standard RL. In this paper, assuming access to a generative model, we derive the sample complexity of RMDPs---when the uncertainty set is measured via either total variation or $\chi^2$ divergence over the full range of uncertainty levels---using a model-based algorithm called distributionally robust value iteration, and develop minimax lower bounds to benchmark its tightness. Our results not only strengthen the prior art in both directions of upper and lower bounds, but also deliver surprising messages that learning RMDPs is not necessarily easier or more difficult than standard MDPs. In the case of total variation, we establish the minimax-optimal sample complexity of RMDPs which is always smaller than that of standard MDPs. In the case of $\chi^2$ divergence, we establish the sample complexity of RMDPs that is tight up to polynomial factors of the effective horizon, and grows linearly with respect to the uncertainty level when it approaches infinity.

LLMs are now an integral part of information retrieval. As such, their role as question answering chatbots raises significant concerns due to their shown vulnerability to adversarial man-in-the-middle (MitM) attacks. Here, we propose the first principled attack evaluation on LLM factual memory under prompt injection via Xmera, our novel, theory-grounded MitM framework. By perturbing the input given to "victim" LLMs in three closed-book and fact-based QA settings, we undermine the correctness of the responses and assess the uncertainty of their generation process. Surprisingly, trivial instruction-based attacks report the highest success rate (up to ~85.3%) while simultaneously having a high uncertainty for incorrectly answered questions. To provide a simple defense mechanism against Xmera, we train Random Forest classifiers on the response uncertainty levels to distinguish between attacked and unattacked queries (average AUC of up to ~96%). We believe that signaling users to be cautious about the answers they receive from black-box and potentially corrupt LLMs is a first checkpoint toward user cyberspace safety.

Abstract-- This paper proposes an uncertainty-aware marine pollution source tracking framework for unmanned surface vehicles (USVs). By integrating high-fidelity marine pollution dispersion simulation with informative path planning techniques, we demonstrate effective identification of pollution sources in marine environments. The proposed approach is implemented based on Robot Operating System (ROS), processing real-time sensor data to update probabilistic source location estimates. Experiments conducted in simulated environments with varying source locations, wave conditions, and starting positions demonstrate the framework's ability to localise pollution sources with high accuracy. Results show that the proposed approach achieves reliable source localisation efficiently and outperforms the existing baseline. This work contributes to the development of full autonomous environmental monitoring capabilities essential for rapid response to marine pollution incidents. Pollution discharged into the marine environment causes severe consequences to ecosystems [1], [2] and human health [3].

First, note that we shall use the same MDPs defined in Appendix D.1 as follows

Branch-and-bound with preactivation splitting has been shown highly effective for deterministic verification of neural networks. In this paper, we extend this framework to the probabilistic setting. We propose BaB-prob that iteratively divides the original problem into subproblems by splitting preactivations and leverages linear bounds computed by linear bound propagation to bound the probability for each subproblem. We prove soundness and completeness of BaB-prob for feedforward-ReLU neural networks. Furthermore, we introduce the notion of uncertainty level and design two efficient strategies for preactivation splitting, yielding BaB-prob-ordered and BaB+BaBSR-prob. We evaluate BaB-prob on untrained networks, MNIST and CIFAR-10 models, respectively, and VNN-COMP 2025 benchmarks. Across these settings, our approach consistently outperforms state-of-the-art approaches in medium- to high-dimensional input problems.

Abstract--Rule-Based Moral Principles for Explaining Uncertainty in Natural Language Generation As large language models (LLMs) are increasingly used in high-stakes applications, the challenge of explaining uncertainty in natural language generation has become both a technical and moral imperative. Traditional approaches rely on probabilistic methods that are often opaque, difficult to interpret, and misaligned with human expectations of transparency and accountability. In response to these limitations, this paper introduces a novel framework based on rule-based moral principles--simple, human-inspired ethical guidelines--for responding to uncertainty in LLM-generated text. Drawing on insights from experimental moral psychology and virtue ethics, we define a set of symbolic behavioral rules such as precaution, deference, and responsibility to guide system responses under conditions of epistemic or aleatoric uncertainty. These rules are implemented declaratively and are designed to generate adaptive, context-sensitive explanations even in the absence of precise confidence metrics. The moral principles are encoded as symbolic rules within a lightweight Prolog-based engine, where each uncertainty tag (low, medium, high) activates an ethically aligned system action along with an automatically generated, plain-language rationale. We evaluate the framework through scenario-based simulations that benchmark rule coverage, assess fairness implications, and analyze trust calibration. An interpretive explanation module is integrated to reveal both the assigned uncertainty level and its underlying justification in a transparent and accessible way. We illustrate the framework through hypothetical yet plausible use cases in clinical and legal domains, demonstrating how rule-based moral reasoning can enhance user trust, promote fairness, and improve the interpretability of AI-generated language. By offering a lightweight, philosophically grounded alternative to probabilistic uncertainty modeling, our approach paves the way for more ethical, human-aligned, and socially responsible natural language generation.

Dialogue systems often fail when user utterances are semantically complete yet lack the clarity and completeness required for appropriate system action. This mismatch arises because users frequently do not fully understand their own needs, while systems require precise intent definitions. This highlights the critical Intent-Action Alignment Problem: determining when an expression is not just understood, but truly ready for a system to act upon. We present STORM, a framework modeling asymmetric information dynamics through conversations between UserLLM (full internal access) and AgentLLM (observable behavior only). STORM produces annotated corpora capturing trajectories of expression phrasing and latent cognitive transitions, enabling systematic analysis of how collaborative understanding develops. Our contributions include: (1) formalizing asymmetric information processing in dialogue systems; (2) modeling intent formation tracking collaborative understanding evolution; and (3) evaluation metrics measuring internal cognitive improvements alongside task performance. Experiments across four language models reveal that moderate uncertainty (40-60%) can outperform complete transparency in certain scenarios, with model-specific patterns suggesting reconsideration of optimal information completeness in human-AI collaboration. These findings contribute to understanding asymmetric reasoning dynamics and inform uncertainty-calibrated dialogue system design.