相关论文: A minimalist account of agency in physics

This paper addresses the critical challenge of mesa-optimization in AI safety by providing a formal definition of agency and a framework for its analysis. Agency is conceptualized as a Continuous Representation of accumulated experience…

This essay discusses the advantages of a probabilistic agent-based approach to questions in theoretical economics, from the nature of economic agents, to the nature of the equilibria supported by their interactions. One idea we propose is…

According to Dennett, the same system may be described using a `physical' (mechanical) explanatory stance, or using an `intentional' (belief- and goal-based) explanatory stance. Humans tend to find the physical stance more helpful for…

Using Promise Theory as a calculus, I review how to define agency in a scalable way, for the purpose of understanding semantic spacetimes. By following simple scaling rules, replacing individual agents with `super-agents' (sub-spaces), it…

While autonomous agents often surpass humans in their ability to handle vast and complex data, their potential misalignment (i.e., lack of transparency regarding their true objective) has thus far hindered their use in critical applications…

We develop a theory of intelligent agency grounded in probabilistic modeling for neural models. Agents are represented as outcome distributions with epistemic utility given by log score, and compositions are defined through weighted…

This paper develops an agent-centric account of measurement that treats the preferred-basis problem is fundamentally perspectival. On this view, the system--apparatus--environment decomposition and the observables that are apt to become…

Agency is widely characterized as the capacity of a system to regulate its internal states toward self-generated goals, yet characterizing the functional basis of this autonomy requires a distinction between the system's own organization…

What is agency, and why does it matter? In this work, we draw from the political science and philosophy literature and give two competing visions of what it means to be an (ethical) agent. The first view, which we term mechanistic, is…

Agentic AI seeks to endow systems with sustained autonomy, reasoning, and interaction capabilities. To realize this vision, its assumptions about agency must be complemented by explicit models of cognition, cooperation, and governance. This…

Agents and agent systems are becoming more and more important in the development of a variety of fields such as ubiquitous computing, ambient intelligence, autonomous computing, intelligent systems and intelligent robotics. The need for…

What are the physical requirements for agency? We investigate whether a purely quantum system (one evolving unitarily in a coherent regime without decoherence or collapse) can satisfy three minimal conditions for agency: an agent must be…

We argue that the analysis of agent/environment interactions should be extended to include the conventions and invariants maintained by agents throughout their activity. We refer to this thicker notion of environment as a lifeworld and…

Powerful artificial intelligence poses an existential threat if the AI decides to drastically change the world in pursuit of its goals. The hope of low-impact artificial intelligence is to incentivize AI to not do that just because this…

The proliferation of agentic artificial intelligence has outpaced the conceptual tools needed to characterize agency in computational systems. Prevailing definitions mainly rely on autonomy and goal-directedness. Here, we argue for a…

An open problem in machine learning is whether flat minima generalize better and how to compute such minima efficiently. This is a very challenging problem. As a first step towards understanding this question we formalize it as an…

Affordances describe the possibilities for an agent to perform actions with an object. While the significance of the affordance concept has been previously studied from varied perspectives, such as psychology and cognitive science, these…

The term 'agent' in artificial intelligence has long carried multiple interpretations across different subfields. Recent developments in AI capabilities, particularly in large language model systems, have amplified this ambiguity, creating…

The rise of LLM-based agents has opened new frontiers in AI applications, yet evaluating these agents remains a complex and underdeveloped area. This survey provides an in-depth overview of the emerging field of LLM agent evaluation,…

As increasingly capable large language model (LLM)-based agents are developed, the potential harms caused by misalignment and loss of control grow correspondingly severe. To address these risks, we propose an approach that directly measures…