Related papers: Active Inference for Physical AI Agents -- An Engi…
AI agents -- systems that combine foundation models with reasoning, planning, memory, and tool use -- are rapidly becoming a practical interface between natural-language intent and real-world computation. This survey synthesizes the…
Recent work has uncovered close links between between classical reinforcement learning algorithms, Bayesian filtering, and Active Inference which lets us understand value functions in terms of Bayesian posteriors. An alternative, but less…
Active inference has emerged as an alternative approach to control problems given its intuitive (probabilistic) formalism. However, despite its theoretical utility, computational implementations have largely been restricted to…
This paper introduces, for the first time to our knowledge, physics-informed neural networks to accurately estimate the AC-OPF result and delivers rigorous guarantees about their performance. Power system operators, along with several other…
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…
Active-passive multiagent systems consist of agents subject to inputs (active agents) and agents with no inputs (passive agents), where active and passive agent roles are considered to be interchangeable in order to capture a wide array of…
Despite their groundbreaking performance, autonomous agents can misbehave when training and environmental conditions become inconsistent, with minor mismatches leading to undesirable behaviors or even catastrophic failures. Robustness…
The Free-Energy Principle (FEP) [1-3] has been adopted in a variety of ambitious proposals that aim to characterize all adaptive, sentient, and cognitive systems within a unifying framework. Judging by the amount of attention it has…
The last few years have witnessed substantial progress in the field of embodied AI where artificial agents, mirroring biological counterparts, are now able to learn from interaction to accomplish complex tasks. Despite this success,…
Engineering workflows such as design optimization, simulation-based diagnosis, control tuning, and model-based systems engineering (MBSE) are iterative, constraint-driven, and shaped by prior decisions. Yet many AI methods still treat these…
More adaptive controllers for robot manipulators are needed, which can deal with large model uncertainties. This paper presents a novel active inference controller (AIC) as an adaptive control scheme for industrial robots. This scheme is…
Inspired by the concept of active learning, we propose active inference$\unicode{x2013}$a methodology for statistical inference with machine-learning-assisted data collection. Assuming a budget on the number of labels that can be collected,…
Enabling robots to explore and act in unfamiliar environments under ambiguous human instructions by interactively identifying task-relevant objects (e.g., identifying cups or beverages for "I'm thirsty") remains challenging for existing…
The rapid advancement of embodied intelligence and world models has intensified efforts to integrate physical laws into AI systems, yet physical perception and symbolic physics reasoning have developed along separate trajectories without a…
The prevailing paradigm in AI for physical systems (scaling general-purpose foundation models toward universal multimodal reasoning) confronts a fundamental barrier at the control interface. Recent benchmarks show that even frontier…
Due to its perceptual limitations, an agent may have too little information about the state of the environment to act optimally. In such cases, it is important to keep track of the observation history to uncover hidden state. Recent deep…
This paper presents a theoretical framework unifying AIXI -- a model of universal AI -- with variational empowerment as an intrinsic drive for exploration. We build on the existing framework of Self-AIXI -- a universal learning agent that…
Humans communicate non-verbally by sharing physical rhythms, such as nodding and gestures, to involve each other. This sharing of physicality creates a sense of unity and makes humans feel involved with others. In this paper, we developed a…
In modern generative-AI workloads, matrix-vector/matrix-matrix multiplications (\emph{MatMul}) dominate the compute and energy cost. Achieving dramatic reductions in energy per token therefore requires a novel, specialized hardware that is…
We explore an active learning approach for dynamic fair resource allocation problems. Unlike previous work that assumes full feedback from all agents on their allocations, we consider feedback from a select subset of agents at each epoch of…