How can reasoning-optimized models preserve their reasoning ability while gaining agentic capabilities?

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

• Reasoning models' capability is tied to their ability to escape saddle points near incorrect solutionsclaim0.814
  Practical interpretive upshot connecting dynamics to model competence.
• 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).claim0.779
  Prediction orthogonality thesis.
• Reasoning models generate performative CoT tokens after achieving strong confidence in their final answer without revealing this belief in textclaim0.762
  The central empirical claim of the paper, supported by activation probing evidence
• The results of abductive reasoning (reduced model priors) can be communicated to other agents as prior beliefs, provided all agents share the same model lexicon or hypothesis space.claim0.751
  Explanation of how knowledge (not just parameters) is shared between agents; links to pre-Cartesian consciousness
• The simple fact that intelligent agents are collectives and do not continue unchanged fulfills a necessary requirement for an open-ended evolution of intelligence.claim0.750
  Connects collective intelligence to evolutionary potential.
• agentic reasoningconcept0.747
  Reasoning approach using code or tool calls executed by an agent.
• does a model's base capability in task-solving predict its capabilities in harness self-evolution?question0.746
  Central framing question motivating the paper's capability decomposition
• Active inference agents can carry out epistemic exploration and account for uncertainty about their environment in a Bayes-optimal fashion.claim0.744
  Abstract and §1, summarizing a key property.