arXiv:2607. 19531v1 Announce Type: cross Abstract: Power grids, markets, and interacting populations, settle into feedback driven equilibria observed through unknown sensors.
Power grids, markets, and interacting populations, settle into feedback driven equilibria observed through unknown sensors. Our Equilibrium Causal Game (ECG) joins a game to its cyclic causal model, hidden inputs, sensor map, and rules for interventions and equilibrium selection; interventions edit declared objects and recompute equilibrium.
arXiv:2606. 04822v1 Announce Type: new Abstract: Causal modeling of physical temporal phenomena must handle interventions that act along trajectories, nonstationary induced laws, path-dependent effects, and feedback mediated by dynamics, all challenging in standard causal models.
arXiv:2607. 07206v2 Announce Type: replace Abstract: Optimizer experiments observe responses to algorithmic configurations without uniquely revealing hidden mechanisms.
arXiv:2608. 11954v1 Announce Type: cross Abstract: Structured potential outcomes such as microscopy images may be recorded after an unknown, unit-specific transformation.
arXiv:2608. 15645v1 Announce Type: new Abstract: Transporting a causal conclusion from a source study population to a target one is a fundamental problem in causal inference.
arXiv:2606. 12502v1 Announce Type: cross Abstract: We propose that value -- the quantity goal-directed agents create, destroy, and exchange -- is a lawful structural quantity in the same category as information.
arXiv:2607. 20708v1 Announce Type: new Abstract: A recent line of work measures causal emergence in reinforcement learning agents through Integrated Information Decomposition, reporting that $\Phi_r$ grows with training and tracks reward improvement.
arXiv:2606. 19386v1 Announce Type: cross Abstract: Runtime monitors for autonomous agents commonly threshold an accumulated internal state - a behavioural baseline, a drift statistic, or, in our prior work, a modelled affective state.
arXiv:2608. 07809v1 Announce Type: new Abstract: A world model is only useful for physical AI if it changes what the agent does, and only safe if it declines to do so when it is wrong.
arXiv:2606. 07552v2 Announce Type: replace-cross Abstract: Large language models exhibit a risk-averse "turtle" bias as strategic agents.
arXiv:2606. 28710v1 Announce Type: new Abstract: We ask under what conditions an agent with a harm-minimizing policy can displace an approval-seeking (RLHF) agent in a competitive market, and when that policy is sufficient to prevent community harm.
arXiv:2606. 08275v1 Announce Type: cross Abstract: When an LLM agent fails -- issues a refund it should not have, calls the wrong tool, leaks data -- existing tooling answers what happened (observability) or whether it passed (evaluation), but not which step caused the failure.