arXiv:2607. 15532v1 Announce Type: new Abstract: Logic and optimization can, in combination, make valuable contributions to rule-based AI.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
The paper presents a doxastic deontic logic designed for autonomous decision‑making under conflicting norms and uncertain information. It extends Chellas' Minimal Deontic Logic with explicit conditional norms and integrates it with multi‑agent KD45 to allow norms to depend on agents’ beliefs about facts and other norms. The authors formulate a Doxastic Norm Compliance Optimization Problem, distinguishing subjective from objective optimization, and identify conditions where the two coincide and where optimal decisions can be computed via weighted partial MaxSAT in polynomial time.
The article surveys rule‑based languages—Datalog, answer set, and probabilistic logic programs—used as the symbolic component of neurosymbolic AI systems. It examines these languages across semantics, expressiveness, neural integration, and evaluation mechanisms, and analyzes over 50 recent systems in databases, machine learning, vision, and robotics. A decision matrix links application scenarios to required features, and the paper concludes with open research problems.
arXiv:2607. 07762v1 Announce Type: new Abstract: Modern machine learning (ML) increasingly relies on complex models whose behavior is difficult to characterize beyond empirical performance metrics.
Modern machine learning (ML) increasingly relies on complex models whose behavior is difficult to characterize beyond empirical performance metrics. Across a wide range of tasks, including prediction, generation, and decision-making, models with similar empirical performance can exhibit markedly different properties in terms of their transparency, interpretability, robustness, fairness, privacy, and certifiability.
arXiv:2605. 04193v2 Announce Type: replace Abstract: Inductive Logic Programming (ILP) aims to learn interpretable first-order rules from data, but existing symbolic and neuro-symbolic approaches struggle to scale to noisy and probabilistic settings.
arXiv:2608. 12325v1 Announce Type: new Abstract: Autonomous reasoning is among the most scientifically and economically motivating topics in AI today.