Related papers: Evaluating Actuators in a Purely Information-Theor…

Web agents hold great potential for automating complex computer tasks, yet their interactions involve long-horizon, sequential decision-making with irreversible actions. In such settings, outcome-based supervision is sparse and delayed,…

This paper discusses an approach to inertial parameter estimation for the case of cargo carrying spacecraft that is based on causal learning, i.e. learning from the responses of the spacecraft, under actuation. Different spacecraft…

The way the brain selects and controls actions is still widely debated. Mainstream approaches based on Optimal Control focus on stimulus-response mappings that optimize cost functions. Ideomotor theory and cybernetics propose a different…

Agentic reinforcement learning trains large language models using multi-turn trajectories that interleave long reasoning traces with short environment-facing actions. Common policy-gradient methods, such as PPO and GRPO, treat each token in…

The rapid development of large language and multimodal models has sparked significant interest in using proprietary models, such as GPT-4o, to develop autonomous agents capable of handling real-world scenarios like web navigation. Although…

Computer use agents (CUAs) have shown strong potential for automating complex digital workflows, yet their training remains constrained by costly live environment interaction and limited high-quality supervision. Existing filtered behavior…

We describe a mechanism to create fair and explainable incentives for software developers to reward contributions to security of a product. We use cooperative game theory to model the actions of the developer team inside a risk management…

A significant challenge in developing AI that can generalize well is designing agents that learn about their world without being told what to learn, and apply that learning to challenges with sparse rewards. Moreover, most traditional…

Physical agents that can autonomously generate engaging, life-like behaviour will lead to more responsive and interesting robots and other autonomous systems. Although many advances have been made for one-to-one interactions in well…

Conventional algorithmic trading systems are grounded in deterministic heuristics or offline-trained statistical models that cannot adapt to the semantic complexity of rapidly shifting market regimes. This paper introduces AGENTICAITA, an…

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…

Symbolic computer vision represents diagrams through explicit logical rules and structured representations, enabling interpretable understanding in machine vision. This requires fundamentally different learning paradigms from pixel-based…

In humans, perceptual awareness facilitates the fast recognition and extraction of information from sensory input. This awareness largely depends on how the human agent interacts with the environment. In this work, we propose active neural…

Reward models play a critical role in guiding large language models toward outputs that align with human expectations. However, an open challenge remains in effectively utilizing test-time compute to enhance reward model performance. In…

We study the mechanism design problem in the setting where agents are rewarded using information only. This problem is motivated by the increasing interest in secure multiparty computation techniques. More specifically, we consider the…

Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to mathematically formalize these abilities using a neural network…

Appropriate ranking algorithms and incentive mechanisms are essential to the creation of high-quality information by users of a social network. However, evaluating such mechanisms in a quantifiable way is a difficult problem. Studies of…

The ability to compute an accurate reward function is essential for optimising a dialogue policy via reinforcement learning. In real-world applications, using explicit user feedback as the reward signal is often unreliable and costly to…

We demonstrate that the algorithmic information content of a system is deeply connected to its potential dynamics, thus affording an avenue for moving systems in the information-theoretic space and controlling them in the phase space. To…

Reinforcement learning agents learn from rewards, but humans can uniquely assign value to novel, abstract outcomes in a goal-dependent manner. However, this flexibility is cognitively costly, making learning less efficient. Here, we propose…