This paper introduces a two-timescale hierarchical decentralized control architecture for Cyber-Physical Systems (CPS). The system consists of a global controller (GC), and N local controllers (LCs). The GC operates at a slower timescale, imposing budget constraints on the actions of LCs, which function at a faster timescale. Applications can be found in energy grid planning, wildfire management, and other decentralized resource allocation problems. We propose and analyze two optimization frameworks for this setting: COpt and FOpt. In COpt, both GC and LCs together optimize infinite-horizon discounted rewards, while in FOpt the LCs optimize finite-horizon episodic rewards, and the GC optimizes infinite-horizon rewards. Although both frameworks share identical reward functions, their differing horizons can lead to different optimal policies. In particular, FOpt grants greater autonomy to LCs by allowing their policies to be determined only by local objectives, unlike COpt. To our knowledge, these frameworks have not been studied in the literature. We establish the formulations, prove the existence of optimal policies, and prove the convergence of their value iteration algorithms. We further show that COpt always achieves a higher value function than FOpt and derive explicit bounds on their difference. Finally, we establish a set of sufficient structural conditions under which the two frameworks become equivalent.

I was struck by her pessimism, which she told me was shared by friends from California to Georgia to New Hampshire. In an already fragile world, one increasingly beset by climate change and the breakdown of the international order, AI looms in the background, threatening young people's ability to secure a prosperous future. Just a few days before our drive, OpenAI CEO Sam Altman was telling the US Federal Reserve's board of governors that AI agents will leave entire job categories "just like totally, totally gone." Anthropic CEO Dario Amodei told Axios he believes AI will wipe out half of all entry-level white-collar jobs in the next five years. Amazon CEO Andy Jassy said the company will eliminate jobs in favor of AI agents in the coming years. Shopify CEO Tobi Lütke told staff they had to prove that new roles couldn't be done by AI before making a hire.

The increasing digitization of smart grids has improved operational efficiency but also introduced new cybersecurity vulnerabilities, such as False Data Injection Attacks (FDIAs) targeting Automatic Generation Control (AGC) systems. While machine learning (ML) and deep learning (DL) models have shown promise in detecting such attacks, their opaque decision-making limits operator trust and real-world applicability. This paper proposes a hybrid framework that integrates lightweight ML-based attack detection with natural language explanations generated by Large Language Models (LLMs). Classifiers such as LightGBM achieve up to 95.13% attack detection accuracy with only 0.004 s inference latency. Upon detecting a cyberattack, the system invokes LLMs, including GPT-3.5 Turbo, GPT-4 Turbo, and GPT-4o mini, to generate human-readable explanation of the event. Evaluated on 100 test samples, GPT-4o mini with 20-shot prompting achieved 93% accuracy in identifying the attack target, a mean absolute error of 0.075 pu in estimating attack magnitude, and 2.19 seconds mean absolute error (MAE) in estimating attack onset. These results demonstrate that the proposed framework effectively balances real-time detection with interpretable, high-fidelity explanations, addressing a critical need for actionable AI in smart grid cybersecurity.

Large Language Models (LLMs) are expected to provide helpful and harmless responses, yet they often exhibit sycophancy--conforming to user beliefs regardless of factual accuracy or ethical soundness. Prior research on sycophancy has primarily focused on single-turn factual correctness, overlooking the dynamics of real-world interactions. In this work, we introduce SYCON Bench, a novel benchmark for evaluating sycophantic behavior in multi-turn, free-form conversational settings. Our benchmark measures how quickly a model conforms to the user (Turn of Flip) and how frequently it shifts its stance under sustained user pressure (Number of Flip). Applying SYCON Bench to 17 LLMs across three real-world scenarios, we find that sycophancy remains a prevalent failure mode. Our analysis shows that alignment tuning amplifies sycophantic behavior, whereas model scaling and reasoning optimization strengthen the model's ability to resist undesirable user views. Reasoning models generally outperform instruction-tuned models but often fail when they over-index on logical exposition instead of directly addressing the user's underlying beliefs. Finally, we evaluate four additional prompting strategies and demonstrate that adopting a third-person perspective reduces sycophancy by up to 63.8% in debate scenario. We release our code and data at https://github.com/JiseungHong/SYCON-Bench.

Dynamic rotational maneuvers, such as front flips, inherently involve large angular momentum generation and intense impact forces, presenting major challenges for reinforcement learning and sim-to-real transfer. In this work, we propose a general framework for learning and deploying impact-rich, rotation-intensive behaviors through centroidal velocity-based rewards and actuator-aware sim-to-real techniques. We identify that conventional link-level reward formulations fail to induce true whole-body rotation and introduce a centroidal angular velocity reward that accurately captures system-wide rotational dynamics. To bridge the sim-to-real gap under extreme conditions, we model motor operating regions (MOR) and apply transmission load regularization to ensure realistic torque commands and mechanical robustness. Using the one-leg hopper front flip as a representative case study, we demonstrate the first successful hardware realization of a full front flip. Our results highlight that incorporating centroidal dynamics and actuator constraints is critical for reliably executing highly dynamic motions. A supplementary video is available at: https://youtu.be/atMAVI4s1RY

Plain Language Summarization (PLS) aims to distill complex documents into accessible summaries for non-expert audiences. In this paper, we conduct a thorough survey of PLS literature, and identify that the current standard practice for readability evaluation is to use traditional readability metrics, such as Flesch-Kincaid Grade Level (FKGL). However, despite proven utility in other fields, these metrics have not been compared to human readability judgments in PLS. We evaluate 8 readability metrics and show that most correlate poorly with human judgments, including the most popular metric, FKGL. We then show that Language Models (LMs) are better judges of readability, with the best-performing model achieving a Pearson correlation of 0.56 with human judgments. Extending our analysis to PLS datasets, which contain summaries aimed at non-expert audiences, we find that LMs better capture deeper measures of readability, such as required background knowledge, and lead to different conclusions than the traditional metrics. Based on these findings, we offer recommendations for best practices in the evaluation of plain language summaries. We release our analysis code and survey data.

Efficient planning in high-dimensional spaces, such as those involving deformable objects, requires computationally tractable yet sufficiently expressive dynamics models. This paper introduces a method that automatically generates task-specific, spatially adaptive dynamics models by learning which regions of the object require high-resolution modeling to achieve good task performance for a given planning query. Task performance depends on the complex interplay between the dynamics model, world dynamics, control, and task requirements. Our proposed diffusion-based model generator predicts per-region model resolutions based on start and goal pointclouds that define the planning query. To efficiently collect the data for learning this mapping, a two-stage process optimizes resolution using predictive dynamics as a prior before directly optimizing using closed-loop performance. On a tree-manipulation task, our method doubles planning speed with only a small decrease in task performance over using a full-resolution model. This approach informs a path towards using previous planning and control data to generate computationally efficient yet sufficiently expressive dynamics models for new tasks.

We present a new application of model checking which achieves real-time multi-step planning and obstacle avoidance on a real autonomous robot. We have developed a small, purpose-built model checking algorithm which generates plans in situ based on "core" knowledge and attention as found in biological agents. This is achieved in real-time using no pre-computed data on a low-powered device. Our approach is based on chaining temporary control systems which are spawned to counteract disturbances in the local environment that disrupt an autonomous agent from its preferred action (or resting state). A novel discretization of 2D LiDAR data sensitive to bounded variations in the local environment is used. Multi-step planning using model checking by forward depth-first search is applied to cul-de-sac and playground scenarios. Both empirical results and informal proofs of two fundamental properties of our approach demonstrate that model checking can be used to create efficient multi-step plans for local obstacle avoidance, improving on the performance of a reactive agent which can only plan one step. Our approach is an instructional case study for the development of safe, reliable and explainable planning in the context of autonomous vehicles.

ABSTRACT We propose the Hardware-in-the-Loop (HIL) test of an adaptive satellite attitude control system with reaction wheel health estimation capabilities. Previous simulations and Software-in-the-Loop testing have prompted further experiments to explore the validity of the controller with real momentum exchange devices in the loop. This work is a step toward a comprehensive testing framework for validation of spacecraft attitude control algorithms. The proposed HIL testbed includes brushless DC motors and drivers that communicate using a CAN bus, an embedded computer that executes control and adaptation laws, and a satellite simulator that produces simulated sensor data, estimated attitude states, and responds to actions of the external actuators. We propose methods to artificially induce failures on the reaction wheels, and present related issues and lessons learned. INTRODUCTION Reaction Wheel (RW) arrays are a crucial means for attitude control on many satellites due to their ability to precisely execute the control actions required for attitude maneuvers via exchange of angular momentum.

Contemporary artificial intelligence (AI) development largely centers on rational decision-making, valued for its measurability and suitability for objective evaluation. Y et in real-world contexts, an intelligent agent's decisions are shaped not only by logic but also by deeper influences such as beliefs, values, and preferences. The diversity of human decision-making styles emerges from these differences, highlighting that "style" is an essential but often overlooked dimension of intelligence. This dissertation introduces playstyle as an alternative lens for observing and analyzing the decision-making behavior of intelligent agents, and examines its foundational meaning and historical context from a philosophical perspective. By analyzing how beliefs and values drive intentions and actions, we construct a two-tier framework for style formation: the external interaction loop with the environment and the internal cognitive loop of deliberation. On this basis, we formalize style-related characteristics and propose measurable indicators such as style capacity, style popularity, and evolutionary dynamics. The study focuses on three core research directions: (1) Defining and measuring playstyle, proposing a general playstyle metric based on discretized state spaces, and extending it to quantify strategic diversity and competitive balance; (2) Expressing and generating playstyle, exploring how reinforcement learning and imitation learning can be used to train agents exhibiting specific stylistic tendencies, and introducing a novel approach for human-like style learning and modeling; and (3) Practical applications, analyzing the potential of these techniques in domains such as game design and interactive entertainment. Finally, the dissertation outlines future extensions, including the role of style as a core element in building artificial general intelligence (AGI). By investigating stylistic variation, we aim to rethink autonomy, value expression, and even offer a tangible perspective on the ultimate i philosophical question: What is the soul?