Related papers: HARP: Measuring Harm Amplification in Multi-Agent …

Large Language Model (LLM)-based Multi-Agent Systems (MAS) have emerged as a powerful paradigm for tackling complex, multi-step tasks across diverse domains. However, despite their impressive capabilities, MAS remain susceptible to…

Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. We characterize the Trojan Hippo attack, a class of persistent memory attacks that operates in a more…

Post-training quantization (PTQ) is essential for deploying LLMs under memory and bandwidth constraints. However, extreme low-bit quantization remains highly sensitive to activation outliers and anisotropic weight curvature. Existing…

Multi-agent systems (MAS) have shown great potential in executing complex tasks, but coordination and safety remain significant challenges. Multi-Agent Reinforcement Learning (MARL) offers a promising framework for agent collaboration, but…

Multi-Agent Reinforcement Learning (MARL) holds significant promise for enabling cooperative driving among Connected and Automated Vehicles (CAVs). However, its practical application is hindered by a critical limitation, i.e., insufficient…

Large language model (LLM) agents are rapidly becoming trusted copilots in high-stakes domains like software development and healthcare. However, this deepening trust introduces a novel attack surface: Agent-Mediated Deception (AMD), where…

Modern industrial systems require updated approaches to safety management, as the tight interplay between cyber-physical, human, and organizational factors has driven their processes toward increasing complexity. In addition to dealing with…

In disaster scenarios, establishing robust emergency communication networks is critical, and unmanned aerial vehicles (UAVs) offer a promising solution to rapidly restore connectivity. However, organizing UAVs to form multi-hop networks in…

Graph topology is a fundamental determinant of memory leakage in multi-agent LLM systems, yet its effects remain poorly quantified. We introduce MAMA (Multi-Agent Memory Attack), a framework that measures how network structure shapes…

Trading off performance guarantees in favor of scalability, the Multi-Agent Path Finding (MAPF) community has recently started to embrace Multi-Agent Reinforcement Learning (MARL), where agents learn to collaboratively generate individual,…

We introduce IMP-MARL, an open-source suite of multi-agent reinforcement learning (MARL) environments for large-scale Infrastructure Management Planning (IMP), offering a platform for benchmarking the scalability of cooperative MARL methods…

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…

Recent advances in multi-agent reinforcement learning (MARL) have created opportunities to solve complex real-world tasks. Cybersecurity is a notable application area, where defending networks against sophisticated adversaries remains a…

This paper proposes a multi-agent reinforcement learning (MARL) approach to learn dynamic dispatching strategies, which is crucial for optimizing throughput in material handling systems across diverse industries. To benchmark our method, we…

Distributed Multi-Agent Path Finding (MAPF) integrated with Multi-Agent Reinforcement Learning (MARL) has emerged as a prominent research focus, enabling real-time cooperative decision-making in partially observable environments through…

Large Language Model (LLM) agents use memory to learn from past interactions, enabling autonomous planning and decision-making in complex environments. However, this reliance on memory introduces a critical security risk: an adversary can…

LLM agents increasingly operate in open-ended environments spanning hundreds of sequential episodes, yet they remain largely stateless: each task is solved from scratch without converting past experience into better future behavior. The…

Autonomous agents powered by large language models (LLMs) have shown impressive capabilities in tool manipulation for complex task-solving. However, existing paradigms such as ReAct rely on sequential reasoning and execution, failing to…

We consider the problem of multi-agent navigation and collision avoidance when observations are limited to the local neighborhood of each agent. We propose InforMARL, a novel architecture for multi-agent reinforcement learning (MARL) which…

Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful…