A model whose objective is prediction can simulate agents who optimize toward any objectives, with any degree of optimality (bounded above but not below by the model's power).

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• acting to optimize value and perception are two aspects of exactly the same principle; namely the minimisation of a quantity [free energy] that bounds the probability of sensory input, given a particular agent or phenotype.quote0.794
  Concise statement of the free-energy principle's unification of action and perception.
• Agents perceive by minimizing variational free energy to ensure model consistency with past observations and act by minimizing expected free energy to make future sensations consistent with preferences.claim0.789
  Formalization of perception-action cycle integrating inference and decision-making.
• Under active inference, the ultimate ‘goal’ is to maintain a coherent phenotype and persist over time, not to maximize reward.claim0.779
  §3, preference learning discussion.
• How can reasoning-optimized models preserve their reasoning ability while gaining agentic capabilities?question0.779
  Core research question motivating the paper's focus on continual RL training of reasoning models rather than base/instruction-tuned models.
• Reinforcement learning can be regarded as a limiting or special case of model-based approaches in general — or active inference in particular — when epistemic value is removed.claim0.777
  §3 Discussion.
• The strict version of the simulation objective is optimized by the actual time evolution rule that created the training samples.claim0.777
  Equivalence of optimal predictor to the physics of the data.
• Active inference agent with learnable preferences developed a strict preference for goals (score +) when the Frisbee location was encountered first, becoming a goal-seeking agent.finding0.776
  Figure 5.4 and text.
• Any system that persists must minimise surprisal, thereby gathering evidence for its own generative model.quote0.776
  Opening sentence defining self-evidencing.