Processes controlled by stochastic synthesis and degradation (SSD) are widespread in biology but their reaction kinetics are not well understood. Using methods borrowed from the theory of resetting processes, we determine the first-passage properties of a collection of independent particles that are synthesized and degraded at constant rates, and follow an arbitrary diffusive process in space. At equal synthesis and degradation rates, the mean reaction time with a target site can be minimized as in stochastic resetting, and a $CV$-criterion is derived. When the degradation rate is held fixed and the synthesis costs are taken into account, an optimal synthesis rate is obtained. In bounded domains, despite particle degradation, SSD improves the mean search time compared to a single non-degrading particle if the synthesis rate exceeds a critical value. The latter obeys a universal relation. We illustrate these findings with Brownian diffusion on the infinite line and in an interval.

Black hole jets represent one of the most extreme manifestations of astrophysical processes, linking accretion physics, relativistic magnetohydrodynamics, and large-scale feedback in galaxies and clusters. Despite decades of observational and theoretical work, the mechanisms governing jet launching, collimation, and energy dissipation remain open questions. In this article, we discuss how upcoming facilities such as the Event Horizon Telescope (EHT), the Cherenkov Telescope Array (CTA), the Vera C. Rubin Observatory (LSST), and the Whole Earth Blazar Telescope (WEBT) will provide unprecedented constraints on jet dynamics, variability, and multi-wavelength signatures. Furthermore, we highlight theoretical challenges, including the role of magnetically arrested disks (MADs), plasma microphysics, and general relativistic magnetohydrodynamic (GRMHD) simulations in shaping our understanding of jet formation. By combining high-resolution imaging, time-domain surveys, and advanced simulations, the next decade promises transformative progress in unveiling the physics of black hole jets.

The deployment of large language models (LLMs) on third-party devices requires new ways to protect model intellectual property. While Trusted Execution Environments (TEEs) offer a promising solution, their performance limits can lead to a critical compromise: using a precomputed, static secret basis to accelerate cryptographic operations. We demonstrate that this mainstream design pattern introduces a classic cryptographic flaw, the reuse of secret keying material, into the system's protocol. We prove its vulnerability with two distinct attacks: First, our attack on a model confidentiality system achieves a full confidentiality break by recovering its secret permutations and model weights. Second, our integrity attack completely bypasses the integrity checks of systems like Soter and TSQP. We demonstrate the practicality of our attacks against state-of-the-art LLMs, recovering a layer's secrets from a LLaMA-3 8B model in about 6 minutes and showing the attack scales to compromise 405B-parameter LLMs across a variety of configurations.

We study first-order phase transitions in continuum Gibbs point processes with saturated interactions. These interactions form a broad class of Hamiltonians in which the local energy in regions of high particle density depends only on the number of points. Building on ideas of Pirogov-Sinai-Zahradnik theory and its adaptations to the continuum, we develop a general method for establishing the existence of two distinct infinite-volume Gibbs measures with different intensities in this setting, demonstrating a first-order phase transition. Our approach extends previous results obtained for the Quermass model and applies in particular to a new class of diluted pairwise interactions introduced in this work.

AI technologies that sense student attention and emotions to enable more personalised teaching interventions are increasingly promoted, but raise pressing questions about student learning, well-being, and ethics. In particular, students' perspectives about AI sensing-intervention in learning are often overlooked. We conducted an online mixed-method experiment with Australian university students (N=132), presenting video scenarios varying by whether sensing was used (in-use vs. not-in-use), sensing modality (gaze-based attention detection vs. facial-based emotion detection), and intervention (by digital device vs. teacher). Participants also completed pairwise ranking tasks to prioritise six core ethical concerns. Findings revealed that students valued targeted intervention but responded negatively to AI monitoring, regardless of sensing methods. Students preferred system-generated hints over teacher-initiated assistance, citing learning agency and social embarrassment concerns. Students' ethical considerations prioritised autonomy and privacy, followed by transparency, accuracy, fairness, and learning beneficence. We advocate designing customisable, social-sensitive, non-intrusive systems that preserve student control, agency, and well-being.

The inclusion of long-range electrostatics in atomistic machine learning (ML) is receiving increasing attention for achieving quantum-mechanical accuracy in predicting a wide range of molecular and material properties. However, there is still no general prescription on how long-range physical effects should be incorporated into the model while preserving well-established locality principles underlying most transferable ML representations. Here, we provide a physical perspective on the problem, by discussing how distinct contributions to the system's electrostatics can be captured through the adoption of different learning paradigms. Specifically, we discern between local charge models, which rely either on explicit charge-density decompositions or implicit auxiliary variables, and models where a notion of nonlocality is deliberately introduced, either via self-consistent procedures or by using nonlocal descriptors and learning architectures. We further address the related aspect of incorporating finite-field effects through the coupling with the system's polarization, relevant for the application of an external electric bias. We conclude by discussing the implications for the simulation of electrochemical interfaces, where long-range electrostatics are essential to capture the interplay between charge redistribution, interfacial dynamics, and ionic screening, and for ionic transport phenomena, which, although less explored, appear far less sensitive to their inclusion.

Reservoir Computing (RC), a type of recurrent random neural network, is a powerful framework for modeling complex and chaotic dynamics. However, its autonomous (closed-loop) operation is often plagued by inherent instability. Moreover, performance is highly sensitive to the reservoir's random initialization, leading to vulnerability to noise and/or behaviour that bears no resemblance whatsoever to the target dynamical system. Here we identify a primary cause of this unreliability: the emergence of excessive, spurious unstable or neutral modes in the closed-loop dynamics. We introduce a simple deterministic input layer design principle that directly addresses this vulnerability by structurally suppressing the emergence of these spurious modes a priori (before training). Our approach dramatically improves robustness to both initialization sensitivity and internal noise, doubling the prediction horizon. Furthermore, we demonstrate on chaotic dynamical systems that this design enables robust estimation of the full Lyapunov spectrum (100\% success rate across 50 seeds), signifying that the autonomous RC faithfully emulates the essential properties of the target dynamical system. This work provides a systematic explanation for a common RC failure mode and offers a concrete design guideline, advancing RCs from heuristic trial-and-error tuning toward a reliable tool for modeling complex systems.

Coherent virtual absorption refers to time-limited storage of optical energy in lossless configurations due to excitation of a complex zero frequency through proper temporal engineering of the incident wave. Given the dynamics underlying the effect and the storage-release mechanism occurring for finite excitation pulses, studying and understanding the associated time dynamics are crucial for enabling future applications. In this work, we carefully investigate this phenomenon in symmetric and asymmetric geometries, shedding light on practical considerations in situations when a closed-form analytical solution is not readily available. Combinations of time domain analysis and spectral filtering are used to enable systematic analysis of these structures. Our approach can be generalized to more complex structures, including multilayered and inhomogeneous cases, providing new opportunities for optimized energy storage and advanced sensing applications utilizing complex-frequency dynamics in lossless designs.

We construct a statistic-swapping involution on the Cartesian product of the generalized symmetric group $S(k,n)$ with the symmetric group $S_{kn}$, which swaps the number of fixed points in the generalized symmetric group element with the number of $k$-cycles in the symmetric group element. This gives a combinatorial proof for a probabilistic observation: the distribution of fixed points on $S(k,n)$ matches the distribution of $k$-cycles on $S_{kn}$.

The present work reports, for the first time, the growth of high-quality free-standing InAsSb nanoflags and their electronic properties. Different growth conditions have been explored, and zinc-blende InAsSb nanoflags of various composition have been obtained. In particular, InAs0.77Sb0.23 nanoflags are on average (2000+-180) nm long, (640+-50) nm wide, and (130+-30) nm thick. We show that these nanoflags have a Landé g-factor larger than InAs and InSb and a mobility comparable to those of the best performing InAs and InSb nanoflags. Besides, we show evidence for a surface Fermi level pinning in the conductance band of these InAs0.77Sb0.23 nanoflags, similar to the well-known behavior of InAs. This promises to make InAsSb easy to couple to superconductors, while keeping or improving many of the features that make InSb an interesting material for quantum applications.

We focus on robust, survivable communication networks, where network links and nodes are affected by an uncertainty set. In this sense, any network links might fail. Besides, a signal can only travel a maximum distance before its quality falls below a certain threshold, necessitating its regeneration by regenerators installed at network nodes. In addition, the price of installing and maintaining regenerators belongs to a discrete uncertainty set. Robust optimization seeks a solution with guaranteed performance against all scenarios modeled in an uncertainty set. Thus, the problem is to find a subset of nodes with minimum cost for the placement of the regenerator, ensuring that all nodes can communicate even if a subset of network links fails. To solve the problem optimally, we propose two solution approaches, including one flow-based and one cut-based integer programming formulation, as well as their iterative exact method. Our theoretical and experimental results show the effectiveness of our methods.

This work investigates generative facial expression interfaces for intelligent agents from a meta-design perspective. We propose the Generative Personalized Facial Expression Interface (GPFEI) framework, which organizes rule-bounded spaces, character identity, and context--expression mapping to address challenges of control, coherence, and alignment in run-time facial expression generation. To operationalize this framework, we developed GenFaceUI, a proof-of-concept tool that enables designers to create templates, apply semantic tags, define rules, and iteratively test outcomes. We evaluated the tool through a qualitative study with twelve designers. The results show perceived gains in controllability and consistency, while revealing needs for structured visual mechanisms and lightweight explanations. These findings provide a conceptual framework, a proof-of-concept tool, and empirical insights that highlight both opportunities and challenges for advancing generative facial expression interfaces within a broader meta-design paradigm.

Multivariate oscillatory signals from complex systems often exhibit non-stationary dynamics and metastable regime structure, making dynamical interpretation challenging. We introduce a ``dynamical microscope'' framework that converts multichannel signals into circular phase--amplitude features, learns a data-driven latent trajectory representation with an autoencoder, and quantifies dynamical regimes through trajectory geometry and flow field metrics. Using a coupled Stuart--Landau oscillator network with topology-switching as ground-truth validation, we demonstrate that the framework recovers differences in dynamical laws even when regimes occupy overlapping regions of state space. Group differences can be expressed as changes in latent trajectory speed, path geometry, and flow organization on a shared manifold, rather than requiring discrete state separation. Speed and explored variance show strong regime discriminability ($η^2 > 0.5$), while some metrics (e.g., tortuosity) capture trajectory geometry orthogonal to topology contrasts. The framework provides a principled approach for analyzing regime structure in multivariate time series from neural, physiological, or physical systems.

Anisotropic, non-thermal, and multi-temperature distributed particle momenta are commonly observed in collisionless space plasmas, such as the solar wind. Using Liouville's theorem, we argue that anisotropic compression or expansion of the plasma, followed by a relaxation of the resulting anisotropic stress must lead to non-equilibrium states that are either anisotropic, non-thermal distribution functions, different electron and ion temperatures, or a combination of these effects. We present arguments showing that a plasma in thermal equilibrium undergoing anisotropic compression or expansion cannot return to thermal equilibrium in the absence of particle collisions. Since most astrophysical plasmas are practically collisionless and experience significant anisotropic compression or expansion, we expect anisotropic, non-thermal, and multi-temperature particle distributions to be ubiquitous, in agreement with solar wind measurements.

Binding energies (BEs) of adsorbates on interstellar dust grains critically control adsorption, desorption, diffusion, and surface reactivity, and therefore strongly influence astrochemical models of star- and planet-forming regions. While recent computational studies increasingly report full distributions of BEs rather than single representative values, these distributions are typically derived for either bare grain surfaces or thick water-ice mantles. In this work, we bridge these regimes by systematically investigating the BE distributions of water on partially and fully ice-covered dust grain surfaces. We employ machine-learning interatomic potentials (MLIPs) based on graph neural networks to model water adsorption on graphene and on the Mg-terminated (010) surface of forsterite, representing carbonaceous and silicate grains, respectively. The models enable extensive sampling of adsorption sites on water clusters, monolayers, and bilayers generated under both crystalline (thermally processed) and amorphous (low-temperature) growth conditions. At submonolayer coverage, the chemical nature of the underlying grain strongly affects both ice morphology and binding energies, with Mg-O interactions on silicate surfaces producing particularly deep binding sites. From monolayer coverage onward, adsorption on both substrates is dominated by hydrogen bonding within the ice, reducing the influence of the grain material. Across all coverages, amorphous ice structures systematically shift the BE distributions toward stronger binding compared to crystalline ice, introducing highly stable defect and pocket sites. These results demonstrate that BE distributions in the submonolayer to few-layer ice regime are broad and highly surface dependent, and they provide physically motivated input for next-generation astrochemical models incorporating surface heterogeneity.

Suppose a Bayesian agent seeks to traverse a graph. Each time she crosses an edge, she pays a price. The first time she reaches a node, there is a payoff. She has an opponent who can reduce the payoffs. This paper uses adversarial risk analysis to find a solution to her route selection problem. It shows how the traveler is advantaged by having an accurate subjective distribution over the costs/payoffs and by having a Bayesian prior for her opponent's strategic choices. The results are relevant to military convoy routing, corporate competition, and certain games.

The Habitable Worlds Observatory (HWO), NASA's next flagship science mission, follows in the tradition of the Nancy Grace Roman Space Telescope and other preceding great observatories. HWO will directly image and characterize Earth-like exoplanet and their atmospheres, with the capability to detect biosignatures and potentially answer the question of whether we are we alone. HWO will also serve as a powerful general astrophysics observatory, enabling breakthroughs in galaxy evolution, stellar astrophysics, and dark matter studies. Currently in pre-formulation, the project has established Exploratory Analytic Cases (EACs), a series of architectural concept designs used to assess the mission's demanding science objectives while exploring challenging engineering parameters. This paper describes the first three EACs, starting with observing strategies and error budget formulation and then progressing to design formulations, trade studies and lessons learned; this paper also discusses the integrated modeling pipeline, a key multidisciplinary system-level analysis capability, and analysis findings as applied to the first EAC. These activities set the stage for the follow on EACs 4 and 5, which will further explore the trade space and prepare for the baseline design that will support the Mission Concept Review (MCR).

We establish a weighted simultaneous Khintchine-type theorem, both convergence and divergence, for all nondegenerate manifolds, which answers a problem posed in [Math. Ann., 337(4):769-796, 2007]. This extends the main results of [Acta Math., 231:1-30, 2023] and [Ann. of Math. (2), 175(1):187-235, 2012] in the weighted set-up. As a by-product of our method, we also obtain a multiplicative Khintchine-type convergence theorem for all nondegenerate manifolds, which is a simultaneous analogue of the celebrated result of Bernik, Kleinbock, and Margulis for dual approximation.

Isomerization in molecular systems almost invariably occurs through 3-dimensional motion due to the nature of chemical bonding. Pseudorotation is an unusual type of isomerization that occurs in some high symmetry systems that gives the appearance of rigid-body rotation yet only involves atom rearrangements. This paper demonstrates that pseudorotation occurs in 2-dimensions in an optical matter (OM) system of metal nanoparticle constituents. The difference in dimensionality of the dynamics arises from the electrodynamic field-interference nature of optical binding vs. quantum mechanical bonding in polyatomic molecules. The 8-nanoparticle OM "kite" structure we study in experiments and simulations has D2 (D2h) symmetry and a D4 symmetric transition state. The mechanism for pseudorotation involves correlated motion of all 8 nanoparticles with smooth (continuous) evolution of their interactions and without particles jumping in or out of the OM array. While the OM kite structure only occurs with 10% probability vs. other OM isomers, its rate of pseudorotation is rapid relative to transitions to other structural isomers (e.g., "teardrop"). The other isomers have structures that lie on a trigonal lattice with inter-particle separations at distances that enhance field interference and induced polarizations. Even though the kite isomer has inter-particle separations that would manifest destructive interference on a particle pair (i.e., 2-body) basis, the kite structure is the slowest to rearrange into any other isomer. We show that the unusual structure and dynamics of the kite optical matter system result from N-body interactions and forces demonstrating that N-body effects are important in this class of active matter and presumably more generally.

Extreme mass ratio inspirals (EMRIs) provide unique probes of near-horizon dissipation through the tidal heating. We present a full Bayesian analysis of tidal heating in equatorial eccentric EMRIs by performing injection-recovery studies and inferring posterior constraints on the reflectivity parameter $|\mathcal{R}|^2$ while sampling in the full EMRI parameter space. We find that in the strong-field regime the posterior uncertainties are smaller, indicating a stronger constraining capability on the tidal heating. Using two-year signals with an optimal signal-to-noise ratio (SNR) of $ρ=50$, EMRIs can put bounds on $|\mathcal{R}|^2$ at the level of $10^{-3}$--$ 10^{-4}$ for a rapidly spinning central object. Moreover, we show that neglecting the tidal heating can induce clear systematic biases in the intrinsic parameters of the EMRI system. These results establish EMRIs as promising precision probes for detecting and constraining black hole event horizons.

We compute the entanglement entropy across a Rindler horizon in scalar field theory with Yukawa interaction. Starting from a microscopic scalar-mediator theory in flat spacetime, we integrate out the massive mediator to obtain a quadratic but nonlocal effective kernel that determines the ground-state wavefunctional. The reduced density matrix for a single Rindler wedge is constructed explicitly by tracing over the complementary wedge, allowing the entanglement entropy to be evaluated directly from the kernel without replica or geometric methods. Exploiting translational invariance parallel to the horizon, the problem decomposes into independent transverse momentum sectors that reduce effectively to one-dimensional nonlocal systems and can be diagonalized analytically in the weak-coupling regime. The interaction-induced entropy obeys an area law, with leading corrections controlled by the Yukawa screening mass and logarithmically sensitive to the transverse ultraviolet cutoff, reflecting the localization of correlations near the horizon. Although the modular Hamiltonian depends on the Rindler acceleration, the entanglement spectrum and entropy are independent of this choice, demonstrating the observer-independent nature of vacuum entanglement. Our framework provides a direct and microscopically transparent approach to computing interaction-induced corrections to horizon entanglement using nonlocal effective kernels.

Agent-based models typically treat systems in isolation, discarding environmental coupling as either computationally prohibitive or dynamically irrelevant. We demonstrate that this neglect misses essential physics: environmental degrees of freedom create memory effects that fundamentally alter system dynamics. By systematically transforming linear update rules into exact generalized Langevin equations, we show that unobserved environmental agents manifest as memory kernels whose timescales and coupling strengths are determined by the environmental interaction spectrum. Network topology shapes this memory structure in distinct ways: small-world rewiring drives dynamics toward a single dominant relaxation mode, while fragmented environments sustain multiple persistent modes corresponding to isolated subpopulations. We apply this framework to covert influence operations where adversaries manipulate target populations exclusively via environmental intermediaries. The steady-state response admits a random-walk interpretation through hitting probabilities, revealing how zealot opinions diffuse through the environment to shift system agent opinions toward the zealot mean - even when zealots never directly contact targets.

We investigate the complexity of the Hamiltonian in the pure $p$-spin spin glass model accompanied with a polynomial-type potential on $\mathbb{R}^N$. In this Hamiltonian, the Gaussian field is anisotropic, and the potential lacks rotational invariance. Our main result derives the logarithmic limit for the expected number of critical points in terms of a variational formula. As a consequence, by identifying the critical location of the phase transition from our representation, we provide an upper bound for the ground state energy of the model.

A string diagram is a two-dimensional graphical representation that can be described as a one-dimensional term generated from a set of primitives using sequential and parallel compositions. Since different syntactic terms may represent the same diagram, this syntax is quotiented by a collection of coherence equations expressing equivalence up to deformation. This work lays foundations for automated reasoning about diagrammatic equivalence, motivated primarily by the verification of quantum circuit equivalences. We consider two classes of diagrams, for which we introduce normalizing term rewriting systems that equate diagrammatically equivalent terms. In both cases, we prove termination and confluence with the help of the proof assistant Isabelle/HOL.

A minimal equicontinuous action of a group $G$ on a Stone space $X$ is called a subodometer. If such a subodometer arises from a group rotation, we refer to it as an odometer. For subodometers $(X,G)$ we show that the hyperspace $\mathcal{H}(X)$ - given by all closed subsets of $X$ and the Vietoris topology - decomposes into subodometers. We show that an infinite subodometer is an odometer if and only if $\mathcal{H}(X)$ decomposes into factors of $(X,G)$. Similarly, we consider $\mathcal{M}(X)$, the space of regular Borel probability measures equipped with the weak-* topology. We show that for a subodometer $(X,G)$ also the connected space $\mathcal{M}(X)$ decomposes into subodometers. We prove that an infinite subodometer $(X,G)$ is an odometer if and only if $\mathcal{M}(X)$ decomposes into factors of $(X,G)$. For this, we study different notions of regular recurrence. Furthermore, we study the disjointness of minimal actions to subodometers and show that this disjointness can be detected from the pairwise disjointness of finite factors. Using this we prove that a minimal action is disjoint from all subodometers if and only if it has a connected maximal equicontinuous factor.

This paper investigates the asymptotic behavior of suitably time-modulated Hawkes processes with heavy-tailed kernels in a nearly unstable regime. We show that, under appropriate scaling, both the intensity processes and the rescaled Hawkes processes converge to a mean-reverting, time-inhomogeneous rough fractional square-root process and its integrated counterpart, respectively. In particular, when the original Hawkes process has a stationary first moment (constant marginal mean), the limiting process takes the form of a time-inhomogeneous rough fractional Cox-Ingersoll-Ross (CIR) equation with a constant mean-reversion parameter and a time-dependent diffusion coefficient. This class of equations is particularly appealing from a practical perspective, especially for the so-called $\textit{fake stationary rough Heston}$ model. We further investigate the properties of such limiting scaled time-inhomogeneous Volterra equations, including moment bounds, path regularity and maximal inequality in the $L^p$ setting for every $p>0$.

In this article, we solve the twisted conjugacy problem with respect to endomorphisms for solvable Baumslag--Solitar groups $BS(1,n)$, i.e., we propose an algorithm which, given two elements $u,v \in BS(1,n)$ and an endomorphism $ψ\in End(BS(1,n))$, decides whether $v=(xψ)^{-1} u x$ for some $x\in BS(1,n)$. Also, we connect the outer fixed points of a given endomorphism $ψ$ with $φ$-twisted conjugacy problem for two words $u, v \in BS(1,n)$, where $φ\in End(BS(1,n))$ and $u, v$ depend on $ψ$. Furthermore, we define the weakly (outer) fixed points and discuss its interplay with the endo-twisted conjugacy problem in $BS(1, n)$.

Understanding the short-range nucleon-nucleon interaction is essential for the interpretation of correlation femtoscopy measurements in high-energy hadronic and nuclear collisions. We present an analytical treatment of the strong interaction in two-nucleon systems by modelling it with a square-well potential and solving the Schroedinger equation in the presence of the Coulomb interaction. The resulting pair wave function is regular at small relative distances and allows for the inclusion of multiple partial waves. We apply this framework to proton-proton femtoscopy and compute theoretical correlation functions for realistic source sizes. We demonstrate that the commonly used Lednicky-Lyuboshits asymptotic approximation overestimates the correlation signal for small sources. Comparisons with numerical calculations using the CATS framework and the Argonne v18 potential show good agreement within current experimental uncertainties. The proposed analytical approach provides a practical and flexible tool for femtoscopic analyses of nucleon and baryon pairs.

Autonomous vehicles (AVs) are characterized by pervasive datafication and surveillance through sensors like in-cabin cameras, LIDAR, and GPS. Drawing on 16 semi-structured interviews with AV drivers analyzed using constructivist grounded theory, this study examines how users make sense of vehicular surveillance within everyday datafication. Findings reveal drivers demonstrate few AV-specific privacy concerns, instead normalizing monitoring through comparisons with established digital platforms. We theorize this indifference by situating AV surveillance within the `surveillance ecology' of platform environments, arguing the datafied car functions as a mobile extension of the `leaky home' -- private spaces rendered permeable through connected technologies continuously transmitting behavioral data. The study contributes to scholarship on surveillance beliefs, datafication, and platform governance by demonstrating how users who have accepted comprehensive smartphone and smart home monitoring encounter AV datafication as just another node in normalized data extraction. We highlight how geographic restrictions on data access -- currently limiting driver log access to California -- create asymmetries that impede informed privacy deliberation, exemplifying `tertiary digital divides.' Finally, we examine how machine learning's reliance on data-intensive approaches creates structural pressure for surveillance that transcends individual manufacturer choices. We propose governance interventions to democratize social learning, including universal data access rights, binding transparency requirements, and data minimization standards to prevent race-to-the-bottom dynamics in automotive datafication.

Large Multimodal Models (LMMs) have shown strong potential for assisting users in tasks, such as programming, content creation, and information access, yet their interaction remains largely limited to traditional interfaces such as desktops and smartphones. Meanwhile, advances in mixed reality (MR) hardware have enabled applications that extend beyond entertainment and into everyday use. However, most existing MR systems rely primarily on manual input (e.g., hand gestures or controllers) and provide limited intelligent assistance due to the lack of integration with large-scale AI models. We present Reality Copilot, a voice-first human-AI assistant for mixed reality that leverages LMMs to enable natural speech-based interaction. The system supports contextual understanding of physical environments, realistic 3D content generation, and real-time information retrieval. In addition to in-headset interaction, Reality Copilot facilitates cross-platform workflows by generating context-aware textual content and exporting generated assets. This work explores the design space of LMM-powered human-AI collaboration in mixed reality.