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

We present Mask Atari, a new benchmark to help solve partially observable Markov decision process (POMDP) problems with Deep Reinforcement Learning (DRL)-based approaches. To achieve a simulation environment for the POMDP problems, Mask…

Learning to cooperate in distributed partially observable environments with no communication abilities poses significant challenges for multi-agent deep reinforcement learning (MARL). This paper addresses key concerns in this domain,…

Task oriented language understanding in dialog systems is often modeled using intents (task of a query) and slots (parameters for that task). Intent detection and slot tagging are, in turn, modeled using sentence classification and word…

Retrieval-Augmented Generation (RAG) systems, which integrate Large Language Models (LLMs) with external knowledge sources, are vulnerable to a range of adversarial attack vectors. This paper examines the importance of RAG systems through…

Conventional multi-agent reinforcement learning (MARL) methods rely on time-triggered execution, where agents sample and communicate actions at fixed intervals. This approach is often computationally expensive and communication-intensive.…

Multi-agent systems have evolved into practical LLM-driven collaborators for many applications, gaining robustness from diversity and cross-checking. However, multi-agent RL (MARL) training is resource-intensive and unstable: co-adapting…

The partially observable Markov decision process (POMDP) provides a principled general model for planning under uncertainty. However, solving a general POMDP is computationally intractable in the worst case. This paper introduces…

We study provable multi-agent reinforcement learning (RL) in the general framework of partially observable stochastic games (POSGs). To circumvent the known hardness results and the use of computationally intractable oracles, we advocate…

A common approach to prediction and planning in partially observable domains is to use recurrent neural networks (RNNs), which ideally develop and maintain a latent memory about hidden, task-relevant factors. We hypothesize that many of…

In this article we propose a qualitative (ordinal) counterpart for the Partially Observable Markov Decision Processes model (POMDP) in which the uncertainty, as well as the preferences of the agent, are modeled by possibility distributions.…

Existing backdoor attacks on Large Language Model-based agents remain stateless, executing fixed behaviors confined to a single session. We propose a stateful agent backdoor that extends the attack lifecycle across multiple sessions under…

The exploration of unknown, Global Navigation Satellite System (GNSS) denied environments by an autonomous communication-aware and collaborative group of Unmanned Aerial Vehicles (UAVs) presents significant challenges in coordination,…

Multi-agent reinforcement learning (MARL) has achieved notable success in cooperative tasks, demonstrating impressive performance and scalability. However, deploying MARL agents in real-world applications presents critical safety…

As large language models (LLMs) are becoming more capable and widespread, the study of their failure cases is becoming increasingly important. Recent advances in standardizing, measuring, and scaling test-time compute suggest new…

Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where individual turns appear benign. We show this attack path leaves an activation-level signature…

The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables remarkable capabilities in natural language processing and generation. However, these systems introduce security vulnerabilities that extend beyond…

The interactive partially observable Markov decision process (I-POMDP) is a recently developed framework which extends the POMDP to the multi-agent setting by including agent models in the state space. This paper argues for formulating the…

A key challenge in non-cooperative multi-agent systems is that of developing efficient planning algorithms for intelligent agents to interact and perform effectively among boundedly rational, self-interested agents (e.g., humans). The…

In many engineering systems, proper predictive maintenance and operational control are essential to increase efficiency and reliability while reducing maintenance costs. However, one of the major challenges is that many sensors are used for…

Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to…