February 2026

Extensive research demonstrates that Deep Reinforcement Learning (DRL) models are susceptible to adversarially constructed inputs (i.e., adversarial examples), which can mislead the agent to take suboptimal or unsafe actions. Recent methods improve attack effectiveness by leveraging future rewards to guide adversarial perturbation generation over sequential time steps (i.e., reward-based attacks). However, these methods are unable to capture dependencies between different time steps in the perturbation generation process, resulting in a weak temporal correlation between the current perturbation and […]

Ver mais

Imagine: You are standing in the checkout line with your credit card in hand after buying groceries and the terminal flashes red and says “Card declined”. You try again and still the same result. You are embarrassed at this point, so you pull out another card. You know you have got plenty of money in your account, but an AI agent somewhere thinks otherwise. Or worse, it thinks you are doing fraud, so it didn’t approve any of […]

Ver mais

Active data acquisition is central to many learning and optimization tasks in deep neural networks, yet remains challenging because most approaches rely on predictive uncertainty estimates that are difficult to obtain reliably. To this end, we propose Goal-Oriented Influence- Maximizing Data Acquisition (GOIMDA), an active acquisition algorithm that avoids explicit posterior inference while remaining uncertainty-aware through inverse curvature. GOIMDA selects inputs by maximizing their expected influence on a user-specified goal functional, such as test loss, predictive entropy, or […]

Ver mais

Agentic Engineering Patterns > “Use red/green TDD” is a pleasingly succinct way to get better results out of a coding agent. TDD stands for Test Driven Development. It’s a programming style where you ensure every piece of code you write is accompanied by automated tests that demonstrate the code works. The most disciplined form of TDD is test-first development. You write the automated tests first, confirm that they fail, then iterate on the implementation until the tests pass. […]

Ver mais

In this paper, we consider the problem of replicable realizable PAC learning. We construct a particularly hard learning problem and show a sample complexity lower bound with a close to $(log|H|)^{3/2}$ dependence on the size of the hypothesis class $H$. Our proof uses several novel techniques and works by defining a particular Cayley graph associated with $H$ and analyzing a suitable random walk on this graph by examining the spectral properties of its adjacency matrix. Furthermore, we show […]

Ver mais