相关论文: Safe Multi-Agent Behavior Must Be Maintained, Not …

LLM-based multi-agent systems have demonstrated remarkable performance on complex tasks through collaborative reasoning. However, these systems tend to rapidly accumulate extremely long conversation histories during interaction. As…

Natural language has long enabled human cooperation, but its lossy, ambiguous, and indirect nature limits the potential of collective intelligence. While machines are not subject to these constraints, most LLM-based multi-agent systems…

Multi-agent systems built on large language models (LLMs) require many coordination choices that are difficult to fix a priori: which skill protocol to invoke, which agent role should perform a subtask, which model to bind to each role, how…

Preventing collisions in multi-robot navigation is crucial for deployment. This requirement hinders the use of learning-based approaches, such as multi-agent reinforcement learning (MARL), on their own due to their lack of safety…

A Multi-Agent System is a distributed system where the agents or nodes perform complex functions that cannot be written down in analytic form. Multi-Agent Systems are highly connected, and the information they contain is mostly stored in…

We present Springdrift, a persistent runtime for long-lived LLM agents. The system integrates an auditable execution substrate (append-only memory, supervised processes, git-backed recovery), a case-based reasoning memory layer with hybrid…

In recent years, Large-Language-Model-driven AI agents have exhibited unprecedented intelligence and adaptability. Nowadays, agents are undergoing a new round of evolution. They no longer act as an isolated island like LLMs. Instead, they…

The rapid advancement of large language model (LLM) agents has raised new concerns regarding their safety and security. In this paper, we propose GuardAgent, the first guardrail agent to protect target agents by dynamically checking whether…

Large Language Model (LLM)-based agents increasingly interact, collaborate, and delegate tasks to one another autonomously with minimal human interaction. Industry guidelines for agentic system governance emphasize the need for users to…

The scarcity of data depicting dangerous situations presents a major obstacle to training AI systems for safety-critical applications, such as construction safety, where ethical and logistical barriers hinder real-world data collection.…

Ensuring robust safety measures across a wide range of scenarios is crucial for user-facing systems. While Large Language Models (LLMs) can generate valuable data for safety measures, they often exhibit distributional biases, focusing on…

Reinsurance decision-making exhibits the core structural properties that motivate multi-agent models: distributed and asymmetric information, partial observability, heterogeneous epistemic responsibilities, simulator-driven environment…

The increasing complexity of regulatory updates from global authorities presents significant challenges for medical device manufacturers, necessitating agile strategies to sustain compliance and maintain market access. Concurrently,…

The accelerating adoption of language models (LMs) as agents for deployment in long-context tasks motivates a thorough understanding of goal drift: agents' tendency to deviate from an original objective. While prior-generation language…

As autonomous and agentic AI systems scale in robotic and human-machine environments, managing hallucination and persistent but unjustified action remains an open challenge. Rather than attributing these failures solely to model or…

Agentic AI will be an essential enabling technology for designing future mobile communication systems, which could provide flexible and customized services, automate complex network operations, and drive autonomous decision-making across…

The rapid proliferation of recent Multi-Agent Systems (MAS), where Large Language Models (LLMs) and Large Reasoning Models (LRMs) usually collaborate to solve complex problems, necessitates a deep understanding of the persuasion dynamics…

Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence. While existing LLM agents depend on text-based mediation for reasoning and communication, we…

Control-flow hijacking attacks manipulate orchestration mechanisms in multi-agent systems into performing unsafe actions that compromise the system and exfiltrate sensitive information. Recently proposed defenses, such as LlamaFirewall,…

Information Retrieval is shifting from passive document ranking toward autonomous agentic workflows that operate in multi-step Reason-Act-Observe loops. In such long-horizon trajectories, minor early errors can cascade, leading to…