相关论文: AGI Agent Safety by Iteratively Improving the Util…

The rapid rise of autonomous AI systems and advancements in agent capabilities are introducing new risks due to reduced oversight of real-world interactions. Yet agent testing remains nascent and is still a developing science. As AI agents…

AI agents increasingly act through external tools: they query databases, execute shell commands, read and write files, and send network requests. Yet in most current agent stacks, model-generated tool calls are handed to the execution layer…

How can we ensure that AI systems are aligned with human values and remain safe? We can study this problem through the frameworks of the AI assistance and the AI shutdown games. The AI assistance problem concerns designing an AI agent that…

A multi-agent AI system (MAS) is composed of multiple autonomous agents that interact, exchange information, and make decisions based on internal generative models. Recent advances in large language models and tool-using agents have made…

How to evaluate Artificial General Intelligence (AGI) is a critical problem that is discussed and unsolved for a long period. In the research of narrow AI, this seems not a severe problem, since researchers in that field focus on some…

With the rapid development of Large Vision Language Models, the focus of Graphical User Interface (GUI) agent tasks shifts from single-screen tasks to complex screen navigation challenges. However, real-world GUI environments, such as PC…

AI agents plan and execute interactions in open-ended environments. For example, OpenAI's Operator can use a web browser to do product comparisons and buy online goods. Much research on making agents useful and safe focuses on directly…

This paper proposes an intent-aware multi-agent planning framework as well as a learning algorithm. Under this framework, an agent plans in the goal space to maximize the expected utility. The planning process takes the belief of other…

Nowadays, agentic AI is emerging as a transformative paradigm for next-generation communication networks, promising to evolve large language models (LLMs) from passive chatbots into autonomous operators. However, unleashing this potential…

AI agents interact with external environments through tool calls, exposing them to attacks like indirect prompt injection that can trigger unauthorized actions. Securing these agents is challenging: they behave autonomously and…

This paper introduces a dynamic and actionable framework for securing agentic AI systems in enterprise deployment. We contend that safety and security are not merely fixed attributes of individual models but also emergent properties arising…

Large language model (LLM)-based AI agents extend LLM capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents. While this empowers agents to perform complex tasks, LLMs may…

AI agents are increasingly used to solve complex, multi-step tasks, but existing multi-agent frameworks remain brittle as workflows grow in scale and depth. Small errors at intermediate stages can propagate through agent interactions, while…

Agentic AI is increasingly being explored and introduced in both manually driven and autonomous vehicles, leading to the notion of Agentic Vehicles (AgVs), with capabilities such as memory-based personalization, goal interpretation,…

Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While…

Addressing complex cooperative tasks in safety-critical environments poses significant challenges for multi-agent systems, especially under conditions of partial observability. We focus on a dynamic network bridging task, where agents must…

Intelligent agents stand out as a potential path toward artificial general intelligence (AGI). Thus, researchers have dedicated significant effort to diverse implementations for them. Benefiting from recent progress in large language models…

Reinforcement learning is increasingly used to transform large language models into agentic systems that act over long horizons, invoke tools, and manage memory under partial observability. While recent work has demonstrated performance…

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…

Power is a key concept in AI safety: power-seeking as an instrumental goal, sudden or gradual disempowerment of humans, power balance in human-AI interaction and international AI governance. At the same time, power as the ability to pursue…