arXiv:2607. 17432v1 Announce Type: new Abstract: Adaptive agents do not always regulate under the same timing conditions.
arXiv:2606. 30975v1 Announce Type: new Abstract: Adaptive agents are usually judged by what they do, but an agent can appear stable while the internal effort required to keep it stable is increasing.
arXiv:2606. 03532v1 Announce Type: cross Abstract: Self on-policy distillation trains a student policy against a teacher derived from its own parameter history, yet the teacher's update schedule -- which governs the \emph{temporal coupling} between teacher and student -- has not been systematically studied as a stability variable.
arXiv:2607. 10608v1 Announce Type: new Abstract: Memory is becoming a core component of long-horizon AI agents, allowing agents to reuse past experience when operating web browsers, software tools, and other interactive environments.
arXiv:2603. 16020v2 Announce Type: replace Abstract: Adaptive agents operating under uncertainty must do more than optimize task outputs: they must maintain a workable internal state under noise, perturbation, and changing conditions.
arXiv:2508. 03875v2 Announce Type: replace Abstract: Many sequential decision problems offer qualitatively different ways of influencing the environment: some interventions act immediately, whereas others induce persistent effects that continue to shape future states long after the decision that initiated them.
arXiv:2606. 30191v1 Announce Type: new Abstract: How does an agent that can tell self from world come to be durably shaped by that distinction?
arXiv:2509. 02655v3 Announce Type: replace-cross Abstract: Many AI alignment discussions of "runaway optimisation" focus on RL agents: unbounded utility maximisers that over-optimise a proxy objective (e.
arXiv:2607. 09685v1 Announce Type: cross Abstract: Policy models often assume that the relationship between a policy instrument and its outcome remains stable across institutional conditions.
arXiv:2602. 01196v2 Announce Type: replace Abstract: Recurrent neural policies are widely used in partially observable control and meta-RL tasks.
arXiv:2607. 26055v1 Announce Type: cross Abstract: Generalist manipulation policies increasingly take the form of action-chunking flow policies built on large pretrained backbones.
arXiv:2607. 09714v1 Announce Type: new Abstract: The Feedback-Coupled Memory Systems (FCMS) architecture formalizes closed-loop coordination through four abstract operators, two of which - the agent update operator $f_i$ and the environmental update operator $\Psi$ - are left axiomatically undefined in the original framework.
arXiv:2607. 04470v1 Announce Type: cross Abstract: Large Language Models (LLMs) offer a natural interface for translating human objectives into reward signals for cooperative multi-agent reinforcement learning (MARL), yet the training-time dynamics of this integration remain poorly understood.