Related papers: Theory of Space: Can Foundation Models Construct S…
Active inference is a process theory of the brain that states that all living organisms infer actions in order to minimize their (expected) free energy. However, current experiments are limited to predefined, often discrete, state spaces.…
The pursuit of artificial general intelligence (AGI) has placed embodied intelligence at the forefront of robotics research. Embodied intelligence focuses on agents capable of perceiving, reasoning, and acting within the physical world.…
Evidence is growing for the theory of embodied cognition, which posits that action and perception co-determine each other, forming an action-perception loop. This suggests that we humans somehow participate in what we perceive. So, how can…
We present some arguments why existing methods for representing agents fall short in applications crucial to artificial life. Using a thought experiment involving a fictitious dynamical systems model of the biosphere we argue that the…
Humans build viewpoint-independent cognitive maps through navigation, enabling intuitive reasoning about object permanence and spatial relations. We argue that multimodal large language models (MLLMs), despite extensive video training, lack…
One of the greatest research challenges of this century is to understand the neural basis for how behavior emerges in brain-body-environment systems. To this end, research has flourished along several directions but have predominantly…
Flexible, goal-directed behavior is a fundamental aspect of human life. Based on the free energy minimization principle, the theory of active inference formalizes the generation of such behavior from a computational neuroscience…
We establish empirical bounds on behavioral inference through controlled experiments at scale: LLM-based agents assigned one of 36 behavioral profiles (9 belief systems x 4 motivations) generate over 1.5 million behavioral sequences across…
The ability to reason under uncertainty and with incomplete information is a fundamental requirement of decision support technology. In this paper we argue that the concentration on theoretical techniques for the evaluation and selection of…
Geospatial data offers immense potential for understanding our planet. However, the sheer volume and diversity of this data along with its varied resolutions, timescales, and sparsity pose significant challenges for thorough analysis and…
The perceived similarity between objects has often been attributed to their physical and conceptual features, such as appearance and animacy, and the theoretical framework of object space is accordingly conceived. Here, we extend this…
Reinforcement Learning has emerged as a strong alternative to solve optimization tasks efficiently. The use of these algorithms highly depends on the feedback signals provided by the environment in charge of informing about how good (or…
Efficient exploration remains a challenging problem in reinforcement learning, especially for those tasks where rewards from environments are sparse. A commonly used approach for exploring such environments is to introduce some "intrinsic"…
Introspection is a foundational cognitive ability, but its mechanism is not well understood. Recent work has shown that AI models can introspect. We study the mechanism of this introspection. We first extensively replicate Lindsey (2025)'s…
This technical note considers the sampling of outcomes that provide the greatest amount of information about the structure of underlying world models. This generalisation furnishes a principled approach to structure learning under a…
We develop a logical framework for reasoning about knowledge and evidence in which the agent may be uncertain about how to interpret their evidence. Rather than representing an evidential state as a fixed subset of the state space, our…
Self-consciousness, the introspection of one's existence and thoughts, represents a high-level cognitive process. As language models advance at an unprecedented pace, a critical question arises: Are these models becoming self-conscious?…
It has been a long-standing dream to design artificial agents that explore their environment efficiently via intrinsic motivation, similar to how children perform curious free play. Despite recent advances in intrinsically motivated…
Large language models (LLMs) and vision language models (VLMs), such as DeepSeek R1,OpenAI o3, and Gemini 2.5 Pro, have demonstrated remarkable reasoning capabilities across logical inference, problem solving, and decision making. However,…
Reinforcement learning systems are often concerned with balancing exploration of untested actions against exploitation of actions that are known to be good. The benefit of exploration can be estimated using the classical notion of Value of…