Stochastic games have become a prevalent framework for studying long-term multi-agent interactions, especially in the context of multi-agent reinforcement learning. In this work, we comprehensively investigate the concept of constant-memory strategies in stochastic games. We first establish some results on best responses and Nash equilibria for behavioral constant-memory strategies, followed by a discussion on the computational hardness of best responding to mixed constant-memory strategies. Those theoretic insights are later verified on several sequential decision-making testbeds, including the $\textit{Iterated Prisoner's Dilemma}$, the $\textit{Iterated Traveler's Dilemma}$, and the $\textit{Pursuit}$ domain. This work aims to enhance the understanding of theoretical issues in single-agent planning under multi-agent systems, and uncover the connection between decision models in single-agent and multi-agent contexts. The code is available at $\texttt{https://github.com/Fernadoo/Const-Mem.}$

The increasing number of satellites and orbital debris has made space congestion a critical issue, threatening satellite safety and sustainability. Challenges such as collision avoidance, station-keeping, and orbital maneuvering require advanced techniques to handle dynamic uncertainties and multi-agent interactions. Reinforcement learning (RL) has shown promise in this domain, enabling adaptive, autonomous policies for space operations; however, many existing RL frameworks rely on custom-built environments developed from scratch, which often use simplified models and require significant time to implement and validate the orbital dynamics, limiting their ability to fully capture real-world complexities. To address this, we introduce OrbitZoo, a versatile multi-agent RL environment built on a high-fidelity industry standard library, that enables realistic data generation, supports scenarios like collision avoidance and cooperative maneuvers, and ensures robust and accurate orbital dynamics. The environment is validated against a real satellite constellation, Starlink, achieving a Mean Absolute Percentage Error (MAPE) of 0.16% compared to real-world data. This validation ensures reliability for generating high-fidelity simulations and enabling autonomous and independent satellite operations.

Generative AI systems are increasingly assisting and acting on behalf of end users in practical settings, from digital shopping assistants to next-generation autonomous cars. In this context, safety is no longer about blocking harmful content, but about preempting downstream hazards like financial or physical harm. Yet, most AI guardrails continue to rely on output classification based on labeled datasets and human-specified criteria,making them brittle to new hazardous situations. Even when unsafe conditions are flagged, this detection offers no path to recovery: typically, the AI system simply refuses to act--which is not always a safe choice. In this work, we argue that agentic AI safety is fundamentally a sequential decision problem: harmful outcomes arise from the AI system's continually evolving interactions and their downstream consequences on the world. We formalize this through the lens of safety-critical control theory, but within the AI model's latent representation of the world. This enables us to build predictive guardrails that (i) monitor an AI system's outputs (actions) in real time and (ii) proactively correct risky outputs to safe ones, all in a model-agnostic manner so the same guardrail can be wrapped around any AI model. We also offer a practical training recipe for computing such guardrails at scale via safety-critical reinforcement learning. Our experiments in simulated driving and e-commerce settings demonstrate that control-theoretic guardrails can reliably steer LLM agents clear of catastrophic outcomes (from collisions to bankruptcy) while preserving task performance, offering a principled dynamic alternative to today's flag-and-block guardrails.

Although average gain optimality is a commonly adopted performance measure in Markov Decision Processes (MDPs), it is often too asymptotic. Further incorporating measures of immediate losses leads to the hierarchy of bias optimalities, all the way up to Blackwell optimality. In this paper, we investigate the problem of identifying policies of such optimality orders. To that end, for each order, we construct a learning algorithm with vanishing probability of error. Furthermore, we characterize the class of MDPs for which identification algorithms can stop in finite time. That class corresponds to the MDPs with a unique Bellman optimal policy, and does not depend on the optimality order considered. Lastly, we provide a tractable stopping rule that when coupled to our learning algorithm triggers in finite time whenever it is possible to do so.

Multi-Agent Deep Reinforcement Learning (MADRL) has shown potential for cooperative and competitive tasks such as autonomous driving and strategic gaming. However, models trained by MADRL are vulnerable to adversarial perturbations on states and actions. Therefore, it is essential to investigate the robustness of MADRL models from an attack perspective. Existing studies focus on either state-only attacks or action-only attacks, but do not consider how to effectively joint them. Simply combining state and action perturbations such as randomly perturbing states and actions does not exploit their potential synergistic effects. In this paper, we propose the State-Action Joint Attack (SAJA) framework that has a good synergistic effects. SAJA consists of two important phases: (1) In the state attack phase, a multi-step gradient ascent method utilizes both the actor network and the critic network to compute an adversarial state, and (2) in the action attack phase, based on the perturbed state, a second gradient ascent uses the critic network to craft the final adversarial action. Additionally, a heuristic regularizer measuring the distance between the perturbed actions and the original clean ones is added into the loss function to enhance the effectiveness of the critic's guidance. We evaluate SAJA in the Multi-Agent Particle Environment (MPE), demonstrating that (1) it outperforms and is more stealthy than state-only or action-only attacks, and (2) existing state or action defense methods cannot defend its attacks.

A fundamental limitation of current AI agents is their inability to learn complex skills on the fly at test time, often behaving like "clever but clueless interns" in novel environments. This severely limits their practical utility. To systematically measure and drive progress on this challenge, we first introduce the Jericho Test-Time Learning (J-TTL) benchmark. J-TTL is a new evaluation setup where an agent must play the same game for several consecutive episodes, attempting to improve its performance from one episode to the next. On J-TTL, we find that existing adaptation methods like reflection, memory, or reinforcement learning struggle. To address the challenges posed by our benchmark, we present EvoTest, an evolutionary test-time learning framework that improves an agent without any fine-tuning or gradients-by evolving the entire agentic system after every episode. EvoTest has two roles: the Actor Agent, which plays the game, and the Evolver Agent, which analyzes the episode transcript to propose a revised configuration for the next run. This configuration rewrites the prompt, updates memory by logging effective state-action choices, tunes hyperparameters, and learns the tool-use routines. On our J-TTL benchmark, EvoTest consistently increases performance, outperforming not only reflection and memory-only baselines but also more complex online fine-tuning methods. Notably, our method is the only one capable of winning two games (Detective and Library), while all baselines fail to win any.

We compare Ising ({-1,+1}) and QUBO ({0,1}) encodings for Boltzmann machine learning under a controlled protocol that fixes the model, sampler, and step size. Exploiting the identity that the Fisher information matrix (FIM) equals the covariance of sufficient statistics, we visualize empirical moments from model samples and reveal systematic, representation-dependent differences. QUBO induces larger cross terms between first- and second-order statistics, creating more small-eigenvalue directions in the FIM and lowering spectral entropy. This ill-conditioning explains slower convergence under stochastic gradient descent (SGD). In contrast, natural gradient descent (NGD)-which rescales updates by the FIM metric-achieves similar convergence across encodings due to reparameterization invariance. Practically, for SGD-based training, the Ising encoding provides more isotropic curvature and faster convergence; for QUBO, centering/scaling or NGD-style preconditioning mitigates curvature pathologies. These results clarify how representation shapes information geometry and finite-time learning dynamics in Boltzmann machines and yield actionable guidelines for variable encoding and preprocessing.

Abstract--Ensuring safe autonomous driving in the presence of occlusions poses a significant challenge in its policy design. While existing model-driven control techniques based on set invariance can handle visible risks, occlusions create latent risks in which safety-critical states are not observable. Data-driven techniques also struggle to handle latent risks because direct mappings from risk-critical objects in sensor inputs to safe actions cannot be learned without visible risk-critical objects. Motivated by these challenges, in this paper, we propose a probabilistic safety certificate for latent risk. Our key technical enabler is the application of probabilistic invariance: It relaxes the strict observability requirements imposed by set-invariance methods that demand the knowledge of risk-critical states. The proposed techniques provide linear action constraints that confine the latent risk probability within tolerance. Such constraints can be integrated into model predictive controllers or embedded in data-driven policies to mitigate latent risks. The proposed method is tested using the CARLA simulator and compared with a few existing techniques. The theoretical and empirical analysis jointly demonstrate that the proposed methods assure long-term safety in real-time control in occluded environments without being overly conservative and with transparency to exposed risks. ISUAL occlusions impose significant challenges in the policy design of autonomous driving.

Automatic Speech Recognition (ASR) has undergone a profound transformation over the past decade, driven by advances in deep learning. This survey provides a comprehensive overview of the modern era of ASR, charting its evolution from traditional hybrid systems, such as Gaussian Mixture Model-Hidden Markov Models (GMM-HMMs) and Deep Neural Network-HMMs (DNN-HMMs), to the now-dominant end-to-end neural architectures. We systematically review the foundational end-to-end paradigms: Connectionist Temporal Classification (CTC), attention-based encoder-decoder models, and the Recurrent Neural Network Transducer (RNN-T), which established the groundwork for fully integrated speech-to-text systems. We then detail the subsequent architectural shift towards Transformer and Conformer models, which leverage self-attention to capture long-range dependencies with high computational efficiency. A central theme of this survey is the parallel revolution in training paradigms. We examine the progression from fully supervised learning, augmented by techniques like SpecAugment, to the rise of self-supervised learning (SSL) with foundation models such as wav2vec 2.0, which drastically reduce the reliance on transcribed data. Furthermore, we analyze the impact of largescale, weakly supervised models like Whisper, which achieve unprecedented robustness through massive data diversity. The paper also covers essential ecosystem components, including key datasets and benchmarks (e.g., LibriSpeech, Switchboard, CHiME), standard evaluation metrics (e.g., Word Error Rate), and critical considerations for real-world deployment, such as streaming inference, on-device efficiency, and the ethical imperatives of fairness and robustness. We conclude by outlining open challenges and future research directions.

GUI agents powered by LLMs show promise in interacting with diverse digital environments. Among these, video games offer a valuable testbed due to their varied interfaces, with adventure games posing additional challenges through complex, narrative-driven interactions. Existing game benchmarks, however, lack diversity and rarely evaluate agents on completing entire storylines. To address this, we introduce FlashAdventure, a benchmark of 34 Flash-based adventure games designed to test full story arc completion and tackle the observation-behavior gap: the challenge of remembering and acting on earlier gameplay information. We also propose CUA-as-a-Judge, an automated gameplay evaluator, and COAST, an agentic framework leveraging long-term clue memory to better plan and solve sequential tasks. Experiments show current GUI agents struggle with full story arcs, while COAST improves milestone completion by bridging the observation-behavior gap. Nonetheless, a marked discrepancy between humans and best-performing agents warrants continued research efforts to narrow this divide.