arXiv AI
Jul 21
Intermittent Control Is Not Diluted Control: A Switching Effect in Artificial Agency
arXiv:2607. 17432v1 Announce Type: new Abstract: Adaptive agents do not always regulate under the same timing conditions.
When Regulation Has Memory: Hysteresis and Control Burden in Artificial Agency
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.
Related stories
arXiv AI
Jun 9
IRAM-Omega-Q: A Computational Framework for Uncertainty Regulation in Adaptive Agents
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 Machine Learning
2d ago
Consistent Model Chasing Is Minimax Optimal: The Exact Value of Scalar Adversarial Adaptive Control under Large Parametric Uncertainty
arXiv:2608. 13651v1 Announce Type: cross Abstract: We solve exactly a fundamental problem of adaptive control against adversarial disturbances: regulate the scalar system $x_{t+1} = ax_t + u_t + w_t$, $x_0=0$, $\|w\|_\infty \le 1$, where the constant pole $a \in [-\Delta, \Delta]$ is unknown in sign and magnitude and $\Delta$ is arbitrarily large.
arXiv AI
Jul 14
The Compliance Trap: Diagnosing How AI Agents Consume Conflicting Memory
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 Machine Learning
Aug 6
Robust Control under Stationary Ambiguity
arXiv:2608. 04832v1 Announce Type: new Abstract: Control policies optimized in simulation can perform poorly in the real system when the parameters $x$ of the simulator are estimated from limited data but the resulting parameter uncertainty is not represented inside the simulation.
arXiv AI
Jul 14
Feedback-Coupled Memory Systems in Continuous Time
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 AI
Jun 9
Oversight Has a Capacity: Calibrating Agent Guards to a Subjective, Fatiguing Human
arXiv:2606. 08919v1 Announce Type: new Abstract: As LLM agents begin to take real, irreversible actions (shell commands, file edits, deploys), the standard safety pattern is a human-in-the-loop approval gate: risky actions pause and wait for a person.
arXiv AI
Jun 30
From Detecting Agency to Doing Work: Self-Caused Credit Builds a Durable Behavioral Self in a Minimal Spiking Agent
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 AI
Jul 14
Transfer Learning Across Policy Regimes in Adaptive Multi-Agent Systems
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 AI
Jul 28
Are You Still the Agent I Authorized? Earned Authority under a Fixed Ceiling for Evolving Agents
arXiv:2607. 23586v1 Announce Type: new Abstract: Long-lived AI agents increasingly evolve after deployment by retaining experience, acquiring skills and tools, revising workflows, delegating work, and moving across task phases.
arXiv AI
Jun 12
Mechanical Conscience: A Mathematical Framework for Dependability of Machine Intelligenc
arXiv:2605. 03847v2 Announce Type: replace Abstract: Distributed collaborative intelligence (DCI), encompassing edge-to-edge architectures, federated learning, transfer learning, and swarm systems, creates environments in which emergent risk is structurally unavoidable: locally correct decisions by individual agents compose into globally unacceptable behavioral trajectories under uncertainty.
arXiv AI
Jul 2
Mechanical Conscience: A Mathematical Framework for Dependability of Machine Intelligence
arXiv:2605. 03847v3 Announce Type: replace Abstract: Distributed collaborative intelligence (DCI), encompassing edge-to-edge architectures, federated learning, transfer learning, and swarm systems, creates environments in which emergent risk is structurally unavoidable: locally correct decisions by individual agents compose into globally unacceptable behavioral trajectories under uncertainty.