Developing models capable of complex, multi-step reasoning is a central goal in artificial intelligence. While representing problems as graphs is a powerful approach, Graph Neural Networks (GNNs) are fundamentally constrained by their message-passing mechanism, which imposes a local bottleneck that limits global, holistic reasoning. We argue that dynamic programming (DP), which solves problems by iteratively refining a global state, offers a more powerful and suitable learning paradigm. We introduce FloydNet, a new architecture that embodies this principle. In […]

Ver mais

arXiv:2602.06103v1 Announce Type: new Abstract: Modern large language models (LLMs) are powerful generators driven by statistical next-token prediction. While effective at producing fluent text, this design biases models toward high-probability continuations rather than exhaustive and faithful answers grounded in source content. As a result, directly applying LLMs lacks systematic mechanisms to ensure both completeness (avoiding omissions) and faithfulness (avoiding unsupported content), which fundamentally conflicts with core AI safety principles. To address this limitation, we present EVE, a structured […]

Ver mais

arXiv:2601.22367v1 Announce Type: new Abstract: Generalized Bayesian Inference (GBI) tempers a loss with a temperature $beta>0$ to mitigate overconfidence and improve robustness under model misspecification, but existing GBI methods typically rely on costly MCMC or SDE-based samplers and must be re-run for each new dataset and each $beta$ value. We give the first fully amortized variational approximation to the tempered posterior family $p_beta(theta mid x) propto pi(theta),p(x mid theta)^beta$ by training a single $(x,beta)$-conditioned neural posterior estimator $q_phi(theta […]

Ver mais

arXiv:2602.15881v1 Announce Type: new Abstract: This paper examines the challenge of embedding public values into national artificial intelligence (AI) governance frameworks, a task complicated by the sociotechnical nature of contemporary systems. As AI permeates domains such as healthcare, justice, and public administration, legitimacy depends not only on technical correctness but on alignment with societal norms, democratic principles, and human dignity. Traditional paradigms focused on model safety or market efficiency neglect broader institutional contexts. To address this, the study […]

Ver mais

arXiv:2602.06209v1 Announce Type: new Abstract: The Weyl closure is a basic operation in algebraic analysis: it converts a system of differential operators with rational coefficients into an equivalent system with polynomial coefficients. In addition to encoding finer information on the singularities of the system, it serves as a preparatory step for many algorithms in symbolic integration. A new algorithm is introduced to approximate the partial Weyl closure of a holonomic module, where the closure is taken with respect […]

Ver mais

Deep reinforcement learning agents are often misaligned, as they over-exploit early reward signals. Recently, several symbolic approaches have addressed these challenges by encoding sparse objectives along with aligned plans. However, purely symbolic architectures are complex to scale and difficult to apply to continuous settings. Hence, we propose a hybrid approach, inspired by humans’ ability to acquire new skills. We use a two-stage framework that injects symbolic structure into neural-based reinforcement learning agents without sacrificing the expressivity of deep […]

Ver mais