Related papers: Adversarial Intent is a Latent Variable: Stateful …

State variables are easily the most subtle dimension of sequential decision problems. This is especially true in the context of active learning problems (bandit problems") where decisions affect what we observe and learn. We describe our…

Autonomous systems are often required to operate in partially observable environments. They must reliably execute a specified objective even with incomplete information about the state of the environment. We propose a methodology to…

Multi-agent deep reinforcement learning makes optimal decisions dependent on system states observed by agents, but any uncertainty on the observations may mislead agents to take wrong actions. The Mean-Field Actor-Critic reinforcement…

Ensuring the safety of embodied AI agents during task planning is critical for real-world deployment, especially in household environments where dangerous instructions pose significant risks. Existing methods often suffer from either high…

Moving target defense (MTD) is a proactive defense approach that aims to thwart attacks by continuously changing the attack surface of a system (e.g., changing host or network configurations), thereby increasing the adversary's uncertainty…

This paper presents an intelligent and adaptive agent that employs deception to recognize a cyber adversary's intent. Unlike previous approaches to cyber deception, which mainly focus on delaying or confusing the attackers, we focus on…

While Large Language Model (LLM) capabilities have scaled, safety guardrails remain largely stateless, treating multi-turn dialogues as a series of disconnected events. This lack of temporal awareness facilitates a "Safety Gap" where…

Recent work explores agentic inference-time techniques to perform structured, multi-step reasoning. However, stateless inference often struggles on multi-step tasks due to the absence of persistent state. Moreover, task-specific fine-tuning…

The joint detection and tracking of a moving target embedded in an unknown disturbance represents a key feature that motivates the development of the cognitive radar paradigm. Building upon recent advancements in robust target detection…

This paper addresses the problem of training a reinforcement learning (RL) policy under partial observability by exploiting a privileged, anytime-feasible planner agent available exclusively during training. We formalize this as a Partially…

Autonomous agents operating in adversarial scenarios face a fundamental challenge: while they may know their adversaries' high-level objectives, such as reaching specific destinations within time constraints, the exact policies these…

Partially observable Markov decision processes (POMDPs) are a general framework for sequential decision-making under latent state uncertainty, yet learning in POMDPs is intractable in the worst case. Motivated by sensing and probing…

Agentic methods have emerged as a powerful and autonomous paradigm that enhances reasoning, collaboration, and adaptive control, enabling systems to coordinate and independently solve complex tasks. We extend this paradigm to safety…

Autonomous agents often operate in scenarios where the state is partially observed. In addition to maximizing their cumulative reward, agents must execute complex tasks with rich temporal and logical structures. These tasks can be expressed…

As LLM-based agents increasingly operate in multi-agent systems, understanding adversarial manipulation becomes critical for defensive design. We present a systematic study of intentional deception as an engineered capability, using…

Various methods for Multi-Agent Reinforcement Learning (MARL) have been developed with the assumption that agents' policies are based on accurate state information. However, policies learned through Deep Reinforcement Learning (DRL) are…

The standard approach for Partially Observable Markov Decision Processes (POMDPs) is to convert them to a fully observed belief-state MDP. However, the belief state depends on the system model and is therefore not viable in reinforcement…

Agentic artificial intelligence (AI) shows promise for automating O-RAN wireless supervisory control, but translated intents still require an executor-side decision before live network actuation. Existing control flows lack explicit…

Large Language Model (LLM) agents increasingly rely on long-term memory and Retrieval-Augmented Generation (RAG) to persist experiences and refine future performance. While this experience learning capability enhances agentic autonomy, it…

This work pioneers regret analysis of risk-sensitive reinforcement learning in partially observable environments with hindsight observation, addressing a gap in theoretical exploration. We introduce a novel formulation that integrates…