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

Mapping deep neural networks (DNNs) to hardware is critical for optimizing latency, energy consumption, and resource utilization, making it a cornerstone of high-performance accelerator design. Due to the vast and complex mapping space,…

To address the global health threat of antimicrobial resistance, antimicrobial peptides (AMP) are being explored for their potent and promising ability to fight resistant pathogens. While artificial intelligence (AI) is being employed to…

There is a growing interest in Multi-Agent Reinforcement Learning (MARL) as the first steps towards building general intelligent agents that learn to make low and high-level decisions in non-stationary complex environments in the presence…

This survey explores the development of meta-thinking capabilities in Large Language Models (LLMs) from a Multi-Agent Reinforcement Learning (MARL) perspective. Meta-thinking self-reflection, assessment, and control of thinking processes is…

While many robotic tasks can be addressed using either centralized single-agent control with full state observation or decentralized multi-agent control, clear criteria for choosing between these approaches remain underexplored. This paper…

LLM-based agents are increasingly deployed in multi-agent systems (MAS). As these systems move toward real-world applications, their security becomes paramount. Existing research largely evaluates single-agent security, leaving a critical…

This paper introduces a novel approach to radio resource allocation in multi-cell wireless networks using a fully scalable multi-agent reinforcement learning (MARL) framework. A distributed method is developed where agents control…

Large Language Model (LLM)-based Multi-Agent Systems (MASs) are increasingly deployed for agentic tasks, such as web automation, itinerary planning, and collaborative problem solving. Yet, their interactive nature introduces new security…

Optimizing large-language model (LLM) training on distributed domain-specific accelerator systems presents significant challenges due to its complex optimization space. Existing optimization methods, however, rely on time-consuming manual…

Large language models (LLMs) are increasingly deployed in multi-agent systems where agents communicate in natural language to solve tasks jointly. A key capability in such systems is consensus formation, where agents iteratively exchange…

Driven by Large Language Models, the single-agent, multi-tool architecture has become a popular paradigm for autonomous agents. However, this architecture introduces a severe privacy risk, which we term Tools Orchestration Privacy Risk…

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding, code generation, and complex planning. Simultaneously, Multi-Agent Systems (MAS) have garnered attention for their potential to enable…

Organisations are starting to adopt LLM-based AI agents, with their deployments naturally evolving from single agents towards interconnected, multi-agent networks. Yet a collection of safe agents does not guarantee a safe collection of…

Multi-Agent Reinforcement Learning (MARL) is increasingly deployed in safety-critical domains, yet methods for interpretable failure detection and attribution remain underdeveloped. We introduce a two-stage gradient-based framework that…

Harness engineering has emerged as an important inference-time technique for large language model (LLM) agents, aiming to improve long-term performance through task decomposition and guided execution. However, more elaborate harnesses are…

Multi-agent Retrieval-Augmented Generation (RAG), wherein each agent takes on a specific role, supports hard queries that require multiple steps and sources, or complex reasoning. Existing approaches, however, rely on static agent behaviors…

Off-policy problems such as policy staleness and training--inference mismatch have become a major bottleneck for training stability and further exploration in LLM RL. The distribution gap between the inference and updated policies grows…

Motivated by the challenge to improve the adversarial robustness, security, and trust of medical decision making intelligent agents, this study develops a full-link security enhancement framework, which describes "input risk perception -…

Large Language Models (LLMs) are increasingly applied in healthcare, yet ensuring their ethical integrity and safety compliance remains a major barrier to clinical deployment. This work introduces a multi-agent refinement framework designed…

Computer use agents are LLM-based agents that can directly interact with a graphical user interface, by processing screenshots or accessibility trees. While these systems are gaining popularity, their safety has been largely overlooked,…