Can models sustain strategic coherence over time, manage resource constraints, and adapt interactively in multi-agent environments with conflicting incentives?

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

• Benchmarks of this kind test whether models can sustain strategic coherence over time, manage resource constraints, and adapt interactively — capabilities that static benchmarks do not measure.claim0.836
  Broader methodological claim about the need for multi-agent, long-horizon benchmarks.
• Strategic coherence, in particular spending efficiency, resource discipline, and phase-adaptive bidding, is associated with rank more strongly than spending volume or any single subskill.quote0.803
  central finding phrased as a load-bearing sentence
• Coherence maximization across simultaneously active mental models is related to prediction error minimization in the FEP, but the relationship is one of compatibility rather than strict equivalenceclaim0.782
  CIMC's position on the relationship between its coherence hypothesis and Friston's FEP
• Strategic coherence in turn (spending efficiency, resource discipline, adaptive phase play) is associated with successclaim0.781
  summary claim linking measured traits to outcomes
• Cost-efficient models lack not individual skills but their reliable integration under competitive pressure.claim0.777
  Interpretation that the tested LLMs have the necessary subskills but cannot coordinate them in the adversarial game.
• We hypothesise that an embodied world model, extending the system in space and time by its interactions with an environment, can be leveraged to maintain coherence.hypothesis0.774
  Proposed solution to the topological limitation, linking embodiment to coherence
• We stress that in today’s models, this capacity is highly unreliable and context-dependent; however, it may continue to develop with further improvements to model capabilities.quote0.769
  Caveat and forward-looking statement from the abstract.
• 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).claim0.765
  Prediction orthogonality thesis.