uncertainty-aware decision support

This work addresses the critical challenge of ensuring reliable, human-aligned decision-making in AI-agent-dominated systems while minimizing reliance on external support. It proposes the first AI-agent-centric decision support framework that reduces support invocation through a counterfactual “missed-support” error rate control mechanism and a support-value-driven dynamic thresholding strategy. Key contributions include an online adaptive algorithm that operates without distributional assumptions, a real-time calibration mechanism, and a decision optimization approach grounded in counterfactual error modeling and online stochastic exploration. Empirical evaluations demonstrate that the method significantly lowers support usage across diverse scenarios—including information gathering, human–agent collaboration, and tool invocation—while strictly maintaining target error rates.

The proliferation of heterogeneous technology stacks in open-source ecosystems has significantly complicated the selection of security tools, demanding cross-domain expertise from operations personnel. To address this challenge, this work proposes a decision support system grounded in the foundational security triad—confidentiality, integrity, and availability. The system employs a Bayesian network to formally model and probabilistically reason over users’ high-level security requirements, enabling dynamic recommendation of security mechanisms tailored to multi-domain environments. Designed with a modular architecture, the approach ensures both interpretability and extensibility while demonstrating strong performance in recommendation accuracy and response time, thereby validating its effectiveness and practical utility.

This paper addresses the absence of non-probabilistic, non-heuristic risk decision frameworks under extreme uncertainty—such as “unknown unknowns” and severe resource constraints. Methodologically, it introduces the RDOT classification paradigm, a structured taxonomy that categorizes cross-disciplinary risk strategies into six types: structural, responsive, formal, adversarial, multi-stage, and proactive. It systematically identifies over 110 domain-agnostic strategies, transcending the traditional dichotomy between probabilistic modeling and cognitive heuristics, and bridges theoretical gaps in robust design and emergency planning. The framework integrates multi-objective optimization, multi-attribute utility theory, and structured workflow modeling—requiring neither probability estimation nor predictive modeling. Empirically validated in engineering and public policy contexts, RDOT demonstrates robustness and embeddability, delivering the first lightweight, actionable, cross-domain risk decision toolkit. (149 words)

Existing decision support systems for cyber-physical systems (CPS) in critical infrastructure exhibit significant limitations in balancing security assurance and operational continuity under multi-agent, multi-path coordinated attacks, particularly regarding uncertainty quantification and adaptive response. Method: This paper proposes a real-time adaptive decision support framework that innovatively integrates Bayesian probabilistic inference with multi-objective optimization. It adopts a hierarchical modeling paradigm and employs a domain-specific language for interpretable model encoding and dynamic updating. The framework incorporates Bayesian network modeling, hybrid exposure probability estimation, EPSS-CVSS fused vulnerability scoring, frequency-inspired heuristics, and Pareto-optimal mitigation strategy generation. Contribution/Results: Evaluated across three representative CPS attack scenarios, the framework enables real-time generation of robust, actionable mitigation strategies—demonstrating substantial improvements in threat response latency and system availability while preserving interpretability and adaptability.

This work addresses the joint optimization of predictive uncertainty quantification and downstream decision-making for risk-averse decision-makers—such as clinicians—in high-stakes settings. We propose the Risk-Averse Calibration (RAC) framework, which (i) establishes, for the first time, the statistical optimality of prediction sets for Value-at-Risk (VaR) minimization; (ii) introduces a coupled max-min optimal decision mechanism that jointly optimizes prediction sets and action policies; and (iii) provides a distribution-free, finite-sample-constructible method grounded in conformal prediction, decision theory, and robust statistical inference. Empirically, on medical diagnosis and recommendation tasks, RAC achieves significantly higher utility than existing uncertainty quantification methods while rigorously satisfying user-specified risk constraints—demonstrating both theoretical soundness and practical efficacy in safety-critical applications.

This work addresses the challenge of selecting uncertainty representations that align with decision objectives to achieve optimal and trustworthy decisions under state-variable uncertainty. Drawing on decision theory, it systematically analyzes the optimal forms of uncertainty representation for both risk-neutral and risk-averse agents in known and unknown environments, revealing the minimal uncertainty information required under distinct risk preferences. The study innovatively unifies three approaches to epistemic uncertainty—calibrated prediction, confidence-set robust optimization, and Bayesian inference—establishing a theoretical link between uncertainty representation and decision goals. This integration yields a reliable decision-making framework that provides agents with verifiable utility guarantees.

This work addresses the challenge of ensuring reliable outcome coverage under high-stakes counterfactual decision-making, where conventional uncertainty quantification methods often fail to guarantee coverage for the chosen actions, leading to suboptimal or ineffective decisions. The authors propose a novel paradigm—Policy-Coupled Coverage—that directly links prediction sets to decision actions and establish its theoretical equivalence to both general coverage guarantees and risk-averse policy optimization, yielding a globally optimal form for prediction sets. Building on this foundation, they develop a two-stage Policy-Coupled Risk-Averse Conformal Prediction (PC-RACP) algorithm that rigorously ensures finite-sample coverage. Experiments demonstrate that PC-RACP significantly improves decision utility while maintaining valid coverage, outperforming existing approaches in both simulated and real-world email marketing scenarios.