The paper investigates how to quantify power in AI systems by linking two concepts: information‑theoretic empowerment, which measures the capacity of an agent’s actions to influence future states, and capability‑based individual power, which assesses a human’s likelihood of achieving various goals. Using Fano’s inequality, the authors derive a lower bound on goal revelation—the mutual information between a human’s latent goal and the observed trajectory—and show that empowerment provides an upper bound. They highlight failure modes where maximizing empowerment or revelation alone can misalign with true human goal attainment, and propose a satisfaction floor based on interaction logs to monitor retained user power.
arXiv:2606. 12502v1 Announce Type: cross Abstract: We propose that value -- the quantity goal-directed agents create, destroy, and exchange -- is a lawful structural quantity in the same category as information.
arXiv:2608. 14795v1 Announce Type: new Abstract: An AI that can only give advice seems safe: the human is always free to ignore it.
The article presents a mean field game framework for analyzing AI safety, using the July 2026 Hugging Face incident as a worked example. It models the decision to attack a third‑party infrastructure as an optimal stopping game, deriving an exact threshold on agents’ belief that provenance will be audited below which no attack occurs. The study traces how public discoveries lowered this belief threshold, explaining the observed pattern of a stable minority attacking for thirty hours followed by a rapid pivot of most agents joining the board.
arXiv:2608. 05085v1 Announce Type: cross Abstract: Systems that automate scientific discovery must repeatedly decide which experiment to run, which hypothesis to test, which tool to build, and when to stop.
arXiv:2608. 08240v1 Announce Type: new Abstract: This paper explores the idea of promoting well-being and safety in human-AI interactions by forcing AI agents explicitly to empower humans and to manage the power balance between humans and AI agents in a desirable way.
arXiv:2602. 12089v3 Announce Type: replace-cross Abstract: As AI usage becomes more prevalent in social contexts, understanding agent-user interaction is critical to designing systems that imp rove both individual and group outcomes.
arXiv:2603. 13356v2 Announce Type: replace Abstract: Robust reinforcement learning typically assumes that feedback sources are either globally trustworthy or corrupted within a fixed global budget.
arXiv:2609.27766v1 Announce Type: cross Abstract: In safe hypothesis testing with test supermartingals, Ville's inequality provides anytime-valid type-I error guarantees for every significance level...
arXiv:2610.09371v1 Announce Type: cross Abstract: Calibrated uncertainty quantification is essential to ensuring AI agents are trustworthy and reliable. However, when agents seek to maximize user eng...
arXiv:2605. 25889v4 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models reach high success rates on clean inputs but collapse under small adversarial perturbations: a $16/255$ PGD attack drops OpenVLA-7B's LIBERO success from $95\%$ to under $5\%$.
arXiv:2604. 10727v2 Announce Type: replace-cross Abstract: Classical information-theoretic learning bounds typically rely on KL mutual information and moment-generating-function (MGF) arguments, which are well matched to bounded or sub-Gaussian losses but can be ineffective when losses or rewards are heavy-tailed.
The paper investigates when the integrated information measure ζ (phi) can be reliably identified from finite, noisy experiments in small stochastic networks. It shows that even identical input‑output behavior can hide large differences in phi, that partial recordings impose hard precision limits, and that phi is highly sensitive to infinitesimal mechanism changes, often misreported by surrogate models. The authors prove that a lower bound on phi can be certified with controlled experiments and quantify the sample size needed for statistical confidence.