When Regulation Has Memory: Hysteresis and Control Burden in Artificial Agency

• URL: http://arxiv.org/abs/2606.30975v1
• Date: Mon, 29 Jun 2026 23:19:26 GMT
• Title: When Regulation Has Memory: Hysteresis and Control Burden in Artificial Agency
• Abstract summary: Two systems may reach similar internal states while one requires much more corrective control to get there.<n>Using a computational model of adaptive uncertainty regulation, we study whether that burden depends on history.<n>Results suggest that adaptive agents should be evaluated not only by whether they remain organized, but by how much regulation they must recruit to do so.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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. This hidden regulatory burden matters for artificial agents operating under noise, delay, or changing demands: two systems may reach similar internal states while one requires much more corrective control to get there. Here, we study whether that burden depends on history. Using a computational model of adaptive uncertainty regulation, we drive an artificial agent through a continuous change in its uncertainty target and then reverse the change without resetting the agent. This creates a simple test for carryover: does the controller respond only to the current target, or does the path by which the agent reached that target still matter? The simulations show a clear history-dependent effect. The adaptive gain required to regulate the agent forms a reproducible hysteresis loop, meaning that the same target can require different levels of control depending on whether the agent is moving toward or returning from a more demanding regime. The timing of regulation also matters. When stabilization is available before disturbance exposure, the agent generally requires less adaptive gain than when it can only recover after disturbance has already acted. The state-level coherence measure also shows path dependence, but the timing effect is much clearer in regulatory gain. The main difference is therefore not that anticipatory regulation produces a completely different state. Rather, it reaches comparable regulated behavior with lower modeled control demand. These results suggest that adaptive agents should be evaluated not only by whether they remain organized, but by how much regulation they must recruit to do so.

Related papers

• Artificial Id: Drive and Persistent Alignment in Agentic AI [0.0]
  Agentic AI is moving from bounded task execution to systems that retain consequential state, continue operating and adapt across task boundaries.<n>We propose an artificial id, an adaptive internal drive for determining whether behavior should continue, stop or change.
  arXiv  Detail & Related papers  (2026-09-10T17:56:41Z)
• Intermittent Control Is Not Diluted Control: A Switching Effect in Artificial Agency [0.0]
  A simple expectation is that an agent moving between these conditions should behave like a weighted average of the two fixed cases.<n>This paper shows that expectation can fail.<n>In a simulated adaptive agent with retained state history, intermittent access to anticipatory control reduces regulatory burden.
  arXiv  Detail & Related papers  (2026-07-19T22:51:44Z)
• Structural Distinguishability of Static and Adaptive Policy Regimes in Agent-Based Regulatory Simulation [0.0]
  This paper contributes a controlled simulation benchmark rather than a new general framework.<n>We evaluate naive fixed policies, tracking-aware fixed policies, and three adaptive controllers: setpoint, safety-margin, and one-sided control.<n>The contribution is methodological: scalar indicators, cap-relative symbolic diagnostics, trajectory motifs, and visual inspection jointly reveal how regulatory conclusions can differ even when average outcomes appear similar.
  arXiv  Detail & Related papers  (2026-06-15T10:06:32Z)
• Learning to Orchestrate Agents under Uncertainty [6.259311190073734]
  We study the problem of adaptive orchestration of heterogeneous agents under uncertainty, where a meta-controller must decide when to delegate to an agent.<n>We propose BOT-Orch, a lightweight framework that recasts orchestration as a bandit problem over agents.<n>We show that the regularised orchestration enjoys $mathcalO(sqrtT)$ regret under standard assumptions, and provably induces preference ordering among agents with identical mean rewards but differing distributional alignment.
  arXiv  Detail & Related papers  (2026-05-26T14:23:22Z)
• Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems [60.79651380135334]
  Long-lived AI agents are increasingly deployed as persistent operational systems.<n>How long does an agent remain reliable after deployment?<n>We introduce AgingBench, a longitudinal reliability benchmark for agent lifespan engineering.
  arXiv  Detail & Related papers  (2026-05-25T19:55:12Z)
• Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment [59.536125286960186]
  Multi-agent frameworks assigning specialized roles are increasingly adopted to enable self-reflection and mutual auditing.<n>We find it simultaneously induces a human-like cognitive bias known as Actor-Observer Asymmetry.<n>ReTAS guides agents to synthesize conflicting viewpoints into an objective consensus.
  arXiv  Detail & Related papers  (2026-04-21T15:05:58Z)
• Layered Mutability: Continuity and Governance in Persistent Self-Modifying Agents [0.0]
  This paper introduces layered mutability, a framework for reasoning about that process across five layers.<n>I report a preliminary ratchet experiment in which reverting an agent's visible self-description after memory accumulation fails to restore baseline behavior.<n>The main implication is that the salient failure mode for persistent self-modifying agents is not abrupt misalignment but compositional drift.
  arXiv  Detail & Related papers  (2026-04-16T07:27:35Z)
• Authority-Level Priors: An Under-Specified Constraint in Hierarchical Predictive Processing [0.0]
  Authority-Level Priors (ALPs) are meta-structural constraints defining a regulatory-admissible subset of identity-level hypotheses.<n>ALPs are not additional representational states nor hyperpriors over precision; they constrain which hypotheses are admissible for regulatory control.<n>A computational formalisation restricts policy optimisation to policies generated by authorised hypotheses.
  arXiv  Detail & Related papers  (2026-03-19T13:27:47Z)
• Improving Search Agent with One Line of Code [68.58667107354253]
  Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools.<n>We propose textbfSearch textbfAgent textbfPolicy textbfOptimization (textbfSAPO), which stabilizes training via a conditional token-level KL constraint.
  arXiv  Detail & Related papers  (2026-03-10T04:07:39Z)
• On the Convergence of Bounded Agents [80.67035535522777]
  A bounded agent has converged when the minimal number of states needed to describe the agent's future behavior cannot decrease. The second view says that a bounded agent has converged just when the agent's performance only changes if the agent's internal state changes.
  arXiv  Detail & Related papers  (2023-07-20T17:27:29Z)
• Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories [88.08381083207449]
  We show the prevalence of emphgeneralization failure on controllable states from stranger agents. We propose a novel method called Self-Trajectory Augmentation (STA), which will reset the environment to the agent's old states according to the Q function during training.
  arXiv  Detail & Related papers  (2023-04-26T10:12:12Z)
• On Controller Tuning with Time-Varying Bayesian Optimization [74.57758188038375]
  We will use time-varying optimization (TVBO) to tune controllers online in changing environments using appropriate prior knowledge on the control objective and its changes. We propose a novel TVBO strategy using Uncertainty-Injection (UI), which incorporates the assumption of incremental and lasting changes. Our model outperforms the state-of-the-art method in TVBO, exhibiting reduced regret and fewer unstable parameter configurations.
  arXiv  Detail & Related papers  (2022-07-22T14:54:13Z)
• Performance of Bounded-Rational Agents With the Ability to Self-Modify [1.933681537640272]
  Self-modification of agents embedded in complex environments is hard to avoid. It has been argued that intelligent agents have an incentive to avoid modifying their utility function so that their future instances work towards the same goals. We show that this result is no longer true for agents with bounded rationality.
  arXiv  Detail & Related papers  (2020-11-12T09:25:08Z)
• Safe Reinforcement Learning via Curriculum Induction [94.67835258431202]
  In safety-critical applications, autonomous agents may need to learn in an environment where mistakes can be very costly. Existing safe reinforcement learning methods make an agent rely on priors that let it avoid dangerous situations. This paper presents an alternative approach inspired by human teaching, where an agent learns under the supervision of an automatic instructor.
  arXiv  Detail & Related papers  (2020-06-22T10:48:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.