Tag
The paper proposes active inference as a framework for AI agents to efficiently acquire context by balancing information gain and cost, with benchmarks on language models and applications in question asking and prompt optimization.
This paper analyzes Active Inference by proving that the Variational Free Energy of an augmented generative model can be decomposed into the predictive model's VFE plus explicit entropy-correction terms, yielding a full variational characterization of Expected Free Energy-based planning. The authors derive a message-passing scheme for EFE-based planning and validate it on grid-world environments.
The paper introduces closed-form predictive coding via hierarchical Gaussian filters that restore precision-weighted prediction errors, yielding faster and more efficient training without global error signals, outperforming backpropagation on certain tasks.
A critical analysis of a company's claim to harness the Casimir force for free energy, explaining why the proposed mechanism is unlikely to yield useful energy.