相关论文: Symmetry-Breaking Augmentations for Ad Hoc Teamwor…

In the future, artificial learning agents are likely to become increasingly widespread in our society. They will interact with both other learning agents and humans in a variety of complex settings including social dilemmas. We argue that…

AI alignment is about ensuring AI systems only pursue goals and activities that are beneficial to humans. Most of the current approach to AI alignment is to learn what humans value from their behavioural data. This paper proposes a…

People frequently face challenging decision-making problems in which outcomes are uncertain or unknown. Artificial intelligence (AI) algorithms exist that can outperform humans at learning such tasks. Thus, there is an opportunity for AI…

The cooperation among AI systems, and between AI systems and humans is becoming increasingly important. In various real-world tasks, an agent needs to cooperate with unknown partner agent types. This requires the agent to assess the…

As AI usage becomes more prevalent in social contexts, understanding agent-user interaction is critical to designing systems that improve both individual and group outcomes. We present an online behavioral experiment (N = 243) in which…

Recent superhuman results in games have largely been achieved in a variety of zero-sum settings, such as Go and Poker, in which agents need to compete against others. However, just like humans, real-world AI systems have to coordinate and…

Artificial intelligence (AI) has revolutionized human cognitive abilities and facilitated the development of new AI entities capable of interacting with humans in both physical and virtual environments. Despite the existence of virtual…

As AI technology continues to develop, more and more agents will become capable of long term autonomy alongside people. Thus, a recent line of research has studied the problem of teaching autonomous agents the concept of ethics and human…

A leading proposal for aligning artificial superintelligence (ASI) is to use AI agents to automate an increasing fraction of alignment research as capabilities improve. We argue that, even when research agents are not scheming to…

With recent advancements in AI and computation tools, intelligent paradigms emerged to empower different fields such as healthcare robots with new capabilities. Advanced AI robotic algorithms (e.g., reinforcement learning) can be trained…

While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves. Agents that assume their partner to be optimal or similar to…

Recent work has shown that, in classification tasks, it is possible to design decision support systems that do not require human experts to understand when to cede agency to a classifier or when to exercise their own agency to achieve…

This paper tackles the critical challenge of human-AI complementarity in decision-making. Departing from the traditional focus on algorithmic performance in favor of performance of the human-AI team, and moving past the framing of…

Ensuring robust decision-making in multi-agent systems is challenging when agents have distinct, possibly conflicting objectives and lack full knowledge of each other's strategies. This is apparent in safety-critical applications such as…

Artificial intelligence is undergoing a structural transformation marked by the rise of agentic systems capable of open-ended action trajectories, generative representations and outputs, and evolving objectives. These properties introduce…

Foundation models have rapidly advanced AI, raising the question of whether their decisions will ultimately surpass human strategies in real-world domains. The exponential, and possibly super-exponential, pace of AI development makes such…

AI support of collaborative interactions entails mediating potential misalignment between interlocutor beliefs. Common preference alignment methods like DPO excel in static settings, but struggle in dynamic collaborative tasks where the…

While the complexity of 21st-century demands has promoted pedagogical approaches to foster complex competencies, a persistent gap remains between in-class learning activities and individualized learning or assessment practices. To address…

Due to the continuously changing environment of service-based applications (SBAs), the ability to adapt to environmental and contextual changes has become a crucial characteristic of such applications. Providing SBAs with this ability is a…

Balancing user agency and system automation is essential for effective human-AI interactions. Fully automated systems can deliver efficiency but risk undermining usability and user autonomy, while purely manual tools are often inefficient…