Deception is a common strategy adapted by autonomous systems in adversarial settings. Existing deception methods primarily focus on increasing opacity or misdirecting agents away from their goal or itinerary. In this work, we propose a deception problem aiming to mislead the robot towards a decoy goal through altering sensor events under a constrained budget of alteration. The environment along with the robot's interaction with it is modeled as a Partially Observable Markov Decision Process (POMDP), and the robot's action selection is governed by a Finite State Controller (FSC). Given a constrained budget for sensor event modifications, the objective is to compute a sensor alteration that maximizes the probability of the robot reaching a decoy goal. We establish the computational hardness of the problem by a reduction from the $0/1$ Knapsack problem and propose a Mixed Integer Linear Programming (MILP) formulation to compute optimal deception strategies. We show the efficacy of our MILP formulation via a sequence of experiments.

This research considers Bayesian decision-analytic approaches toward the traversal of an uncertain graph. Namely, a traveler progresses over a graph in which rewards are gained upon a node's first visit and costs are incurred for every edge traversal. The traveler knows the graph's adjacency matrix and his starting position but does not know the rewards and costs. The traveler is a Bayesian who encodes his beliefs about these values using a Gaussian process prior and who seeks to maximize his expected utility over these beliefs. Adopting a decision-analytic perspective, we develop sequential decision-making solution strategies for this coupled information-collection and network-routing problem. We show that the problem is NP-Hard and derive properties of the optimal walk. These properties provide heuristics for the traveler's problem that balance exploration and exploitation. We provide a practical case study focused on the use of unmanned aerial systems for public safety and empirically study policy performance in myriad Erdos-Renyi settings.

Deep learning techniques have improved performance beyond conventional methods in a wide variety of tasks. However, for neural networks in particular, it is not straightforward to assign network-induced uncertainty on their output as a function of network architecture, training algorithm, and initialization [1]. One approach to uncertainty quantification (UQ) is to treat any individual network as a draw from an ensemble, and identify the systematic uncertainty with the variance in the neural network outputs over the ensemble [2, 3]. This variance can certainly be measured empirically by training a large ensemble of networks, but it would be advantageous to be able to predict it from first principles. This is possible in the infinite-width limit of multi-layer perceptron (MLP) architectures, where the statistics of the network outputs after training are Gaussian with mean and variance determined by the neural tangent kernel (NTK) [4-6]. For realistic MLPs with large but finite width n, one can compute corrections to this Gaussian distribution that are perturbative in 1/n [7].

The rapid adoption of AI systems presents enterprises with a dual challenge: accelerating innovation while ensuring responsible governance. Current AI governance approaches suffer from fragmentation, with risk management frameworks that focus on isolated domains, regulations that vary across jurisdictions despite conceptual alignment, and high-level standards lacking concrete implementation guidance. This fragmentation increases governance costs and creates a false dichotomy between innovation and responsibility. We propose the Unified Control Framework (UCF): a comprehensive governance approach that integrates risk management and regulatory compliance through a unified set of controls. The UCF consists of three key components: (1) a comprehensive risk taxonomy synthesizing organizational and societal risks, (2) structured policy requirements derived from regulations, and (3) a parsimonious set of 42 controls that simultaneously address multiple risk scenarios and compliance requirements. We validate the UCF by mapping it to the Colorado AI Act, demonstrating how our approach enables efficient, adaptable governance that scales across regulations while providing concrete implementation guidance. The UCF reduces duplication of effort, ensures comprehensive coverage, and provides a foundation for automation, enabling organizations to achieve responsible AI governance without sacrificing innovation speed.

Finetuning provides a scalable and cost-effective means of customizing language models for specific tasks or response styles, with greater reliability than prompting or in-context learning. In contrast, the conventional wisdom is that injecting knowledge via finetuning results in brittle performance and poor generalization. We argue that the dichotomy of "task customization" (e.g., instruction tuning) and "knowledge injection" (e.g., teaching new facts) is a distinction without a difference. We instead identify concrete factors that explain the heterogeneous effectiveness observed with finetuning. To this end, we conduct a large-scale experimental study of finetuning the frontier Gemini v1.5 model family on a spectrum of datasets that are artificially engineered to interpolate between the strengths and failure modes of finetuning. Our findings indicate that question-answer training data formats provide much stronger knowledge generalization than document/article-style training data, numerical information can be harder for finetuning to retain than categorical information, and models struggle to apply finetuned knowledge during multi-step reasoning even when trained on similar examples -- all factors that render "knowledge injection" to be especially difficult, even after controlling for considerations like data augmentation and information volume. On the other hand, our findings also indicate that it is not fundamentally more difficult to finetune information about a real-world event than information about what a model's writing style should be.

Mixture of large language model (LLMs) Agents (MoA) architectures achieve state-of-the-art performance on prominent benchmarks like AlpacaEval 2.0 by leveraging the collaboration of multiple LLMs at inference time. Despite these successes, an evaluation of the safety and reliability of MoA is missing. We present the first comprehensive study of MoA's robustness against deceptive LLM agents that deliberately provide misleading responses. We examine factors like the propagation of deceptive information, model size, and information availability, and uncover critical vulnerabilities. On AlpacaEval 2.0, the popular LLaMA 3.1-70B model achieves a length-controlled Win Rate (LC WR) of 49.2% when coupled with 3-layer MoA (6 LLM agents). However, we demonstrate that introducing only a $\textit{single}$ carefully-instructed deceptive agent into the MoA can reduce performance to 37.9%, effectively nullifying all MoA gains. On QuALITY, a multiple-choice comprehension task, the impact is also severe, with accuracy plummeting by a staggering 48.5%. Inspired in part by the historical Doge of Venice voting process, designed to minimize influence and deception, we propose a range of unsupervised defense mechanisms that recover most of the lost performance.

This Perspective explores the transformative potential of Multi-Agent Systems (MAS) powered by Large Language Models (LLMs) in the geosciences. Users of geoscientific data repositories face challenges due to the complexity and diversity of data formats, inconsistent metadata practices, and a considerable number of unprocessed datasets. MAS possesses transformative potential for improving scientists' interaction with geoscientific data by enabling intelligent data processing, natural language interfaces, and collaborative problem-solving capabilities. We illustrate this approach with "PANGAEA GPT", a specialized MAS pipeline integrated with the diverse PANGAEA database for Earth and Environmental Science, demonstrating how MAS-driven workflows can effectively manage complex datasets and accelerate scientific discovery. We discuss how MAS can address current data challenges in geosciences, highlight advancements in other scientific fields, and propose future directions for integrating MAS into geoscientific data processing pipelines. In this Perspective, we show how MAS can fundamentally improve data accessibility, promote cross-disciplinary collaboration, and accelerate geoscientific discoveries.

Large Language Models (LLMs) have achieved remarkable success, but their English-centric training data limits performance in non-English languages, highlighting the need for enhancements in their multilingual capabilities. While some work on multilingual prompting methods handles non-English queries by utilizing English translations or restructuring them to more closely align with LLM reasoning patterns, these works often overlook the importance of cultural context, limiting their effectiveness. To address this limitation, we propose EMCEI, a simple yet effective approach that improves LLMs' multilingual capabilities by incorporating cultural context for more accurate and appropriate responses. Specifically, EMCEI follows a two-step process that first extracts relevant cultural context from the LLM's parametric knowledge via prompting. Then, EMCEI employs an LLM-as-Judge mechanism to select the most appropriate response by balancing cultural relevance and reasoning ability. Experiments on diverse multilingual benchmarks show that EMCEI outperforms existing baselines, demonstrating its effectiveness in handling multilingual queries with LLMs.

Many reinforcement learning (RL) algorithms require large amounts of data, prohibiting their use in applications where frequent interactions with operational systems are infeasible, or high-fidelity simulations are expensive or unavailable. Meanwhile, low-fidelity simulators--such as reduced-order models, heuristic reward functions, or generative world models--can cheaply provide useful data for RL training, even if they are too coarse for direct sim-to-real transfer. We propose multi-fidelity policy gradients (MFPGs), an RL framework that mixes a small amount of data from the target environment with a large volume of low-fidelity simulation data to form unbiased, reduced-variance estimators (control variates) for on-policy policy gradients. We instantiate the framework by developing multi-fidelity variants of two policy gradient algorithms: REINFORCE and proximal policy optimization. Experimental results across a suite of simulated robotics benchmark problems demonstrate that when target-environment samples are limited, MFPG achieves up to 3.9x higher reward and improves training stability when compared to baselines that only use high-fidelity data. Moreover, even when the baselines are given more high-fidelity samples--up to 10x as many interactions with the target environment--MFPG continues to match or outperform them. Finally, we observe that MFPG is capable of training effective policies even when the low-fidelity environment is drastically different from the target environment. MFPG thus not only offers a novel paradigm for efficient sim-to-real transfer but also provides a principled approach to managing the trade-off between policy performance and data collection costs.

Rapid advances in AI are beginning to reshape national security. Destabilizing AI developments could rupture the balance of power and raise the odds of great-power conflict, while widespread proliferation of capable AI hackers and virologists would lower barriers for rogue actors to cause catastrophe. Superintelligence -- AI vastly better than humans at nearly all cognitive tasks -- is now anticipated by AI researchers. Just as nations once developed nuclear strategies to secure their survival, we now need a coherent superintelligence strategy to navigate a new period of transformative change. We introduce the concept of Mutual Assured AI Malfunction (MAIM): a deterrence regime resembling nuclear mutual assured destruction (MAD) where any state's aggressive bid for unilateral AI dominance is met with preventive sabotage by rivals. Given the relative ease of sabotaging a destabilizing AI project -- through interventions ranging from covert cyberattacks to potential kinetic strikes on datacenters -- MAIM already describes the strategic picture AI superpowers find themselves in. Alongside this, states can increase their competitiveness by bolstering their economies and militaries through AI, and they can engage in nonproliferation to rogue actors to keep weaponizable AI capabilities out of their hands. Taken together, the three-part framework of deterrence, nonproliferation, and competitiveness outlines a robust strategy to superintelligence in the years ahead.