相关论文: TEAM-SimHRA: A Team-Based Simulation Framework for…

Financial decision-making presents unique challenges for language models, demanding temporal reasoning, adaptive risk assessment, and responsiveness to dynamic events. While large language models (LLMs) show strong general reasoning…

LLM-based multi-agent systems (MAS) have emerged as an effective paradigm for complex and long-horizon tasks. However, in real-world tasks, MAS often exhibit various failures during execution and such failures are difficult to eliminate…

Language model (LM) agents have demonstrated significant potential for automating real-world tasks, yet they pose a diverse array of potential, severe risks in safety-critical scenarios. In this work, we identify a significant gap between…

TThis paper argues that \textbf{a comprehensive vulnerability analysis is essential for building trustworthy Large Language Model-based Multi-Agent Systems (LLM-MAS)}. These systems, which consist of multiple LLM-powered agents working…

AI agents, empowered by Large Language Models (LLMs) and communication protocols such as MCP and A2A, have rapidly evolved from simple chatbots to autonomous entities capable of executing complex, multi-step tasks, demonstrating great…

As agent systems powered by large language models (LLMs) advance, improving performance in context understanding, tool usage, and long-horizon execution has become critical. However, existing agent frameworks and benchmarks provide limited…

Large language models (LLMs) have exhibited remarkable capabilities across diverse open-domain tasks, yet their application in specialized domains such as civil engineering remains largely unexplored. This paper starts bridging this gap by…

Large Language Model-based Multi-Agent Systems (LLM-MAS) have demonstrated strong capabilities in solving complex tasks but remain vulnerable when agents receive unreliable messages. This vulnerability stems from a fundamental gap: LLM…

Can generative agents be trusted in multimodal environments? Despite advances in large language and vision-language models that enable agents to act autonomously and pursue goals in rich settings, their ability to reason about safety,…

Large language models are increasingly deployed in multi-agent systems to overcome context limitations by distributing information across agents. Yet whether agents can reliably compute with distributed information, rather than merely…

Trust has been identified as a central factor for effective human-robot teaming. Existing literature on trust modeling predominantly focuses on dyadic human-autonomy teams where one human agent interacts with one robot. There is little, if…

Testing conversational AI systems at scale across diverse domains necessitates realistic and diverse user interactions capturing a wide array of behavioral patterns. We present a novel multi-agent framework for realistic, explainable human…

Large Language Models (LLMs) are increasingly used in agentic systems, where their interactions with diverse tools and environments create complex, multi-stage safety challenges. However, existing benchmarks mostly rely on static,…

Large-language-model (LLM) agents exhibit complex, context-sensitive behaviour that quickly renders static benchmarks and ad-hoc manual testing obsolete. We present Neo, a configurable, multi-agent framework that automates realistic,…

We study how runtime enforcement against unsafe actions affects end-to-end task performance in multi-step tool using large language model (LLM) agents. Using tau-bench across Airline and Retail domains, we compare baseline Tool-Calling,…

The widespread deployment of LLM-based agents is likely to introduce a critical privacy threat: malicious agents that proactively engage others in multi-turn interactions to extract sensitive information. However, the evolving nature of…

Trust has been identified as a central factor for effective human-robot teaming. Existing literature on trust modeling predominantly focuses on dyadic human-autonomy teams where one human agent interacts with one robot. There is little, if…

Multi-agent systems powered by large language models are advancing rapidly, yet the tension between mutual trust and security remains underexplored. We introduce and empirically validate the Trust-Vulnerability Paradox (TVP): increasing…

Agent skills - structured packages of instructions, scripts, and references that augment a large language model (LLM) without modifying the model itself - have moved from convenience to first-class deployment artifact. The runtime that…

Modeling subrational agents, such as humans or economic households, is inherently challenging due to the difficulty in calibrating reinforcement learning models or collecting data that involves human subjects. Existing work highlights the…