Related papers: Emergence in Multi-Agent Systems: A Safety Perspec…

Regardless of past learning, an agent in an open world will face unfamiliar events outside of prior experience, existing models, or policies. Further, the agent will sometimes lack relevant knowledge and/or sufficient time to assess the…

Active-passive multiagent systems consist of agents subject to inputs (active agents) and agents with no inputs (passive agents), where active and passive agent roles are considered to be interchangeable in order to capture a wide array of…

Any autonomous controller will be unsafe in some situations. The ability to quantitatively identify when these unsafe situations are about to occur is crucial for drawing timely human oversight in, e.g., freight transportation applications.…

We consider adaptive decision-making problems where an agent optimizes a cumulative performance objective by repeatedly choosing among a finite set of options. Compared to the classical prediction-with-expert-advice set-up, we consider…

Multi-agent reinforcement learning (MARL) has achieved notable success in cooperative tasks, demonstrating impressive performance and scalability. However, deploying MARL agents in real-world applications presents critical safety…

Control and planning of multi-agent systems is an active and increasingly studied topic of research, with many practical applications such as rescue missions, security, surveillance, and transportation. This thesis addresses the planning…

The efficient market hypothesis (EMH), based on rational expectations and market equilibrium, is the dominant perspective for modelling economic markets. However, the most notable critique of the EMH is the inability to model periods of…

Emergent behavior arising in a joint human-robot system cannot be fully predicted based on an understanding of the individual agents. Typically, robot behavior is governed by algorithms that optimize a reward function that should…

As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…

Failure attribution is essential for diagnosing and improving multi-agent systems (MAS), yet existing benchmarks and methods largely assume a single deterministic root cause for each failure. In practice, MAS failures often admit multiple…

Many systems involve numerous interacting parts and the whole system can have properties that the individual parts do not. I take this novelty as the defining characteristic of an emergent property. Other characteristics associated with…

The recent adoption of machine learning as a tool in real world decision making has spurred interest in understanding how these decisions are being made. Counterfactual Explanations are a popular interpretable machine learning technique…

In this paper, we study the problem of learning to satisfy temporal logic specifications with a group of agents in an unknown environment, which may exhibit probabilistic behaviour. From a learning perspective these specifications provide a…

In multi-agent systems, agents observe data, and use them to make inferences and take actions. As a result sensing and control naturally interfere, more so from a real-time perspective. A natural consequence is that in multi-agent systems…

Several recent works have found the emergence of grounded compositional language in the communication protocols developed by mostly cooperative multi-agent systems when learned end-to-end to maximize performance on a downstream task.…

We study the problem of consensus emergence in multi-agent systems via external feedback controllers. We consider a set of agents interacting with dynamics given by a Cucker-Smale type of model, and study its consensus stabilization by…

As Large Language Model (LLM) agents become more widespread, associated misalignment risks increase. While prior research has studied agents' ability to produce harmful outputs or follow malicious instructions, it remains unclear how likely…

Designing, assuring and releasing safe automated vehicles is a highly interdisciplinary process. As complex systems, automated driving systems will inevitably be subject to emergent properties, i. e., the properties of the overall system…

The real world is awash with multi-agent problems that require collective action by self-interested agents, from the routing of packets across a computer network to the management of irrigation systems. Such systems have local incentives…

As artificial intelligence scales, the concepts of alignment, agency, and autonomy have become central to AI safety, governance, and control. However, even in human contexts, these terms lack universal definitions, varying across…