Related papers: Auditing Cascading Risks in Multi-Agent Systems vi…
Accurate interpretation of clinical narratives is critical for patient care, but the complexity of these notes makes automation challenging. While Large Language Models (LLMs) show promise, single-model approaches can lack the robustness…
Multi-Agent Reinforcement Learning (MARL) has emerged as a foundational approach for addressing diverse, intelligent control tasks in various scenarios like the Internet of Vehicles, Internet of Things, and Unmanned Aerial Vehicles.…
This paper establishes and explores a framework to analyze the risk of cascading failures in a platoon of autonomous vehicles, accounting for communication time-delays and input uncertainty. Our proposed framework yields closed-form…
Traditional video coding (VVC, HEVC) prioritizes human visual perception, transmitting substantial texture redundancy that severely hinders machine decision-making under constrained bandwidths. In dynamic channels, this redundancy causes…
When considering risky events or actions, we must not downplay the role of involved objects: a charged battery in our phone averts the risk of being stranded in the desert after a flat tyre, and a functional firewall mitigates the risk of a…
Out-of-time-order correlator (OTOC), been suggested as a measure of quantum information scrambling in quantum many-body systems, has received enormous attention recently. The experimental measurement of OTOC is quite challenging. The…
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…
Large language model (LLM)-powered multi-agent systems (MAS) have demonstrated cognitive and execution capabilities that far exceed those of single LLM agents, yet their capacity for self-evolution remains hampered by underdeveloped memory…
With recent advances in Large Language Models (LLMs), Agentic AI has become phenomenal in real-world applications, moving toward multiple LLM-based agents to perceive, learn, reason, and act collaboratively. These LLM-based Multi-Agent…
Automatic open-domain dialogue evaluation has attracted increasing attention, yet remains challenging due to the complexity of assessing response appropriateness. Traditional evaluation metrics, typically trained with true positive and…
Recent years have witnessed the rapid development of Large Language Model-based Multi-Agent Systems (MAS), which excel at collaborative decision-making and complex problem-solving. However, malicious agents in MAS may inject misinformation…
Large Language Model-based Multi-Agent Systems (MASs) have emerged as a powerful paradigm for tackling complex tasks through collaborative intelligence. However, the topology of these systems--how agents in MASs should be configured,…
A critical limitation in large-scale multi-agent systems is the cascading of errors. And without intermediate verification, downstream agents exacerbate upstream inaccuracies, resulting in significant quality degradation. To bridge this…
Autoregressive (AR) models have shown great promise in image generation, yet they face a fundamental inefficiency stemming from their core component: a vast, unstructured vocabulary of visual tokens. This conventional approach treats tokens…
Air Traffic Control (ATC) is a safety-critical domain in which incorrect interpretation of instructions may lead to severe operational consequences. While large language models (LLMs) demonstrate strong general performance, their…
User-centric evaluation has become a key paradigm for assessing Conversational Recommender Systems (CRS), aiming to capture subjective qualities such as satisfaction, trust, and rapport. To enable scalable evaluation, recent work…
Multi-Agent Reinforcement Learning (MARL) has emerged as a powerfulparadigm for cooperative decision-making in connected autonomous vehicles(CAVs); however, existing approaches often fail to guarantee stability, optimality,and…
Epidemiologic studies often evaluate the association between an exposure and an event risk. When time-varying, exposure updates usually occur at discrete visits although changes are in continuous time and survival models require values to…
A stochastic approach based on generalized Polynomial Chaos (gPC) is used to quantify the error in Large-Eddy Simulation (LES) of a spatially-evolving mixing layer flow and its sensitivity to different simulation parameters, viz. the grid…
Iterative LLM systems(self-refinement, chain-of-thought, autonomous agents) are increasingly deployed, yet their temporal dynamics remain uncharacterized. Prior work evaluates task performance at convergence but ignores the trajectory: how…