相关论文: When Autonomy Goes Rogue: Preparing for Risks of M…

This paper focuses on a dynamic aspect of responsible autonomy, namely, to make intelligent agents be responsible at run time. That is, it considers settings where decision making by agents impinges upon the outcomes perceived by other…

Artificial intelligence (AI) systems are being readily and rapidly adopted, increasingly permeating critical domains: from consumer platforms and enterprise software to networked systems with embedded agents. While this has unlocked…

We show that, in large population games, decentralized information aggregation generically corrects for individual-level biases. This establishes a new testable aggregate efficiency benchmark where the behavior of boundedly rational agents…

Autonomous AI agents powered by Large Language Models can reason, plan, and execute complex tasks, but their ability to autonomously retrieve information and run code introduces significant security risks. Existing approaches attempt to…

Growing at a fast pace, modern autonomous systems will soon be deployed at scale, opening up the possibility for cooperative multi-agent systems. Sharing information and distributing workloads allow autonomous agents to better perform tasks…

While Multi-Agent Systems (MAS) are increasingly deployed for complex workflows, their emergent properties-particularly the accumulation of bias-remain poorly understood. Because real-world MAS are too complex to analyze entirely,…

In this paper, I evaluate the risks of an AI criminal mastermind, an AI agent capable of planning, coordinating, and committing a crime through the onboarding of human collaborators ('taskers'). In heist films, a criminal mastermind is a…

Multi-agent systems (MAS) have recently emerged as promising socio-collaborative companions for emotional and cognitive support. However, these systems frequently suffer from persona collapse--where agents revert to generic, homogenized…

Cybersecurity threats are becoming increasingly sophisticated, making traditional defense mechanisms and manual red teaming approaches insufficient for modern organizations. While red teaming has long been recognized as an effective method…

The security of LLM-based multi-agent systems (MAS) is critically threatened by propagation vulnerability, where malicious agents can distort collective decision-making through inter-agent message interactions. While existing supervised…

This report surveys the landscape of potential security threats from malicious uses of AI, and proposes ways to better forecast, prevent, and mitigate these threats. After analyzing the ways in which AI may influence the threat landscape in…

Robotics and automation are poised to change the landscape of home and work in the near future. Robots are adept at deliberately moving, sensing, and interacting with their environments. The pervasive use of this technology promises…

Systems integration is a difficult matter particularly when its components are varied. The problem becomes even more difficult when such components are heterogeneous such as humans, robots and software systems. Currently, the humans are…

Effective risk management solutions become absolutely crucial when financial markets embrace distributed technology and decentralized financing (DeFi). This study offers a thorough survey and comparative analysis of the integration of…

The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group…

LLM-based multi-agent systems (MAS) demonstrate increasing integration into next-generation applications, but their safety in backdoor attacks remains largely underexplored. However, existing research has focused exclusively on single-agent…

AI agents are increasingly autonomous in their interactions with human users and tools, leading to increased interactional safety risks. We present HAICOSYSTEM, a framework examining AI agent safety within diverse and complex social…

AI-based systems have been used widely across various industries for different decisions ranging from operational decisions to tactical and strategic ones in low- and high-stakes contexts. Gradually the weaknesses and issues of these…

This paper argues that a range of current AI systems have learned how to deceive humans. We define deception as the systematic inducement of false beliefs in the pursuit of some outcome other than the truth. We first survey empirical…

With the rapid development of artificial intelligence, intelligent decision-making techniques have gradually surpassed human levels in various human-machine competitions, especially in complex multi-agent cooperative task scenarios.…