相关论文: Shutdownable Agents through POST-Agency

This paper studies whether a planner who only has information about the network topology can discriminate among agents according to their network position. The planner proposes a simple menu of contracts, one for each location, in order to…

The goal of this research is to develop agents that are adaptive and predictable and timely. At first blush, these three requirements seem contradictory. For example, adaptation risks introducing undesirable side effects, thereby making…

While multi-agent trust region algorithms have achieved great success empirically in solving coordination tasks, most of them, however, suffer from a non-stationarity problem since agents update their policies simultaneously. In contrast, a…

We argue that accountability mechanisms are needed in human-AI agent relationships to ensure alignment with user and societal interests. We propose a framework according to which AI agents' engagement is conditional on appropriate user…

We consider the problem of collectively delivering some message from a specified source to a designated target location in a graph, using multiple mobile agents. Each agent has a limited energy which constrains the distance it can move.…

AI agents that interact with the real world through tool calls pose fundamental safety challenges: agents might leak private information, cause unintended side effects, or be manipulated through prompt injection. To address these…

I consider motivation and value-alignment in AI systems from the perspective of (constrained) entropy maximization. Though the structures encoding knowledge in any physical system can be understood as energetic constraints, only living…

Agents in an open system communicate using interaction protocols. Suppose that we have a system of agents and that we want to add a new protocol that all (or some) agents should be able to understand. Clearly, modifying the source code for…

Motivated by growing evidence of agents' mistakes in strategically simple environments, we propose a solution concept -- robust equilibrium -- that requires only an asymptotically optimal behavior. We use it to study large random matching…

An intelligent agent may in general pursue multiple procedural goals simultaneously, which may lead to arise some conflicts (incompatibilities) among them. In this paper, we focus on the incompatibilities that emerge due to resources…

We study a mechanism-design problem in which spiteful agents strive to not only maximize their rewards but also, contingent upon their own payoff levels, seek to lower the opponents' rewards. We characterize all individually rational (IR)…

In the coming years, AI agents will be used for making more complex decisions, including in situations involving many different groups of people. One big challenge is that AI agent tends to act in its own interest, unlike humans who often…

If capable AI agents are generally incentivized to seek power in service of the objectives we specify for them, then these systems will pose enormous risks, in addition to enormous benefits. In fully observable environments, most reward…

Physical inactivity remains a critical global health issue, yet scalable strategies for sustained motivation are scarce. Conversational agents designed as simulated exercising peers (SEPs) represent a promising alternative, but their…

Scientists and philosophers have debated whether humans can trust advanced artificial intelligence (AI) agents to respect humanity's best interests. Yet what about the reverse? Will advanced AI agents trust humans? Gauging an AI agent's…

In this paper, we consider a robust action selection problem in multi-agent systems where performance must be guaranteed when the system suffers a worst-case attack on its agents. Specifically, agents are tasked with selecting actions from…

A principal who values an object allocates it to one or more agents. Agents learn private information (signals) from an information designer about the allocation payoff to the principal. Monetary transfer is not available but the principal…

In repeated games, such as auctions, players rely on autonomous learning agents to choose their actions. We study settings in which players have their agents make monetary transfers to other agents during play at their own expense, in order…

In multi-agent planning, agents jointly compute a plan that achieves mutual goals, keeping certain information private to the individual agents. Agents' coordination is achieved through the transmission of messages. These messages can be a…

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…