When Can Safe Controllers Adapt? Information before Commitment

• URL: http://arxiv.org/abs/2607.16895v1
• Date: Sat, 18 Jul 2026 17:30:41 GMT
• Title: When Can Safe Controllers Adapt? Information before Commitment
• Abstract summary: We study safe adaptive control under a safety guarantee on the learning trajectory itself.<n>Performance is measured against a safe oracle that knows the realized model.<n>We prove recovery in special cases and derive semidefinite upper certificates for deterministic linear-Gaussian systems.
• Score: 26.556002437630426
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Safe adaptive control is online adaptation under a safety guarantee on the learning trajectory itself. The controller may use any causal, history-dependent rule and act differently across environments as data arrive. Only its safety guarantee is uniform: the same rule must satisfy it under every initially plausible model. Performance is measured against a safe oracle that knows the realized model. Many finite-time analyses assume persistent excitation of the uniformly safe closed loop, so the data distinguish every pair of models requiring different control decisions. Under that assumption, feasibility is already settled; only the rate remains. We ask instead: Do the safety constraints permit such an informative experiment at all? While an alternative remains plausible, the controller must preserve a safe continuation under it. We call the first action that forecloses such a continuation commitment. Chance safety allows commitment only on an event rare under the alternative, and the evidence must arrive beforehand: the observation generated by the committing action is too late. We define precommitment information as the KL divergence between learner-visible laws stopped before commitment. Our main result is a causal reduction. The commitment rule determines (1) the probability that safety permits commitment under the alternative, (2) the target-side cost of remaining noncommittal, (3) and the information available when the decision is made. Bounded precommitment information therefore leaves a fixed fraction of the oracle gap unavoidable. If the gap is Ω(T), every uniformly safe policy has linear regret. We establish the obstruction in a constrained linear system with quadratic regulation cost. We also prove recovery in special cases and derive semidefinite upper certificates for deterministic linear-Gaussian systems.

Related papers

• SafeCommit: Certifying When Memory-Grounded Agents May Safely Act [0.10742675209112619]
  We introduce SafeCommit, a risk controlled layer between agent reasoning and external execution.<n>It permits a side effectful action only when a conformal action certificate shows that the action is safe in every retained world.<n>A dependency-free controlled simulator illustrates the safety-utility tradeoff and reproduces all reported results with one command.
  arXiv  Detail & Related papers  (2026-08-04T23:44:35Z)
• What Can Be Enforced? A Theory of Certified Runtime Safety for Tool-Using Agents [0.0]
  guardrails act before irreversible tool calls, but their guarantees depend on what policy state is representable.<n>Pearson representation attacks add a margin, so benign calibration alone does not transfer.<n>Experiments target these distinctions through static diagnostics, controlled-model enumeration, representation rewrites, and paired closed-loop reruns.
  arXiv  Detail & Related papers  (2026-07-24T19:14:26Z)
• Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs [54.96236442484317]
  We show that hazardous knowledge can be retained in the model and behaviorally gated by a privileged control token.<n>Our method, Token Inoculation, introduces a binding-and-branching approach.
  arXiv  Detail & Related papers  (2026-07-21T02:15:39Z)
• Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation [52.122731171289665]
  We introduce the first framework for cross-model safety steering.<n>Our pipeline never accesses unsafe data on the target side.<n>We evaluate our approach in text-to-image and text-to-video generation across diverse source-target model pairs.
  arXiv  Detail & Related papers  (2026-06-03T18:00:04Z)
• Conformal Policy Control [50.46542384484142]
  We show how to use any safe reference policy as a probabilistic regulator for any optimized but untested policy.<n>Unlike conservative optimization methods, we do not assume the user has identified the correct model class.<n>Our experiments on applications ranging from natural language question answering to biomolecular engineering show that safe exploration is possible from the first moment of deployment.
  arXiv  Detail & Related papers  (2026-03-02T18:54:36Z)
• Building a Foundational Guardrail for General Agentic Systems via Synthetic Data [76.18834864749606]
  LLM agents can plan multi-step tasks, intervening at the planning stage-before any action is executed-is often the safest way to prevent harm.<n>Existing guardrails mostly operate post-execution, which is difficult to scale and leaves little room for controllable supervision at the plan level.<n>We introduce AuraGen, a controllable engine that synthesizes benign trajectories, injects category-labeled risks with difficulty, and filters outputs via an automated reward model.
  arXiv  Detail & Related papers  (2025-10-10T18:42:32Z)
• Core Safety Values for Provably Corrigible Agents [2.6451153531057985]
  We introduce the first implementable framework for corrigibility, with provable guarantees in multi-step, partially observed environments.<n>Our framework replaces a single reward with five *structurally separate* utility heads.<n>For open-ended settings where adversaries can modify the agent, we prove that deciding whether an arbitrary post-hack agent will ever violate corrigibility is undecidable.
  arXiv  Detail & Related papers  (2025-07-28T16:19:25Z)
• From Uncertain to Safe: Conformal Fine-Tuning of Diffusion Models for Safe PDE Control [16.249515106834355]
  Deep learning for partial differential equation (PDE)-constrained control is gaining increasing attention.<n>We propose Safe Diffusion Models for PDE Control (SafeDiffCon) to achieve optimal control under safety constraints.<n>We evaluate SafeDiffCon on three control tasks: 1D Burgers' equation, 2D incompressible fluid, and controlled nuclear fusion problem.
  arXiv  Detail & Related papers  (2025-02-04T10:42:30Z)
• SaFormer: A Conditional Sequence Modeling Approach to Offline Safe Reinforcement Learning [64.33956692265419]
  offline safe RL is of great practical relevance for deploying agents in real-world applications. We present a novel offline safe RL approach referred to as SaFormer.
  arXiv  Detail & Related papers  (2023-01-28T13:57:01Z)
• Recursively Feasible Probabilistic Safe Online Learning with Control Barrier Functions [60.26921219698514]
  We introduce a model-uncertainty-aware reformulation of CBF-based safety-critical controllers. We then present the pointwise feasibility conditions of the resulting safety controller. We use these conditions to devise an event-triggered online data collection strategy.
  arXiv  Detail & Related papers  (2022-08-23T05:02:09Z)
• Fail-Safe Adversarial Generative Imitation Learning [9.594432031144716]
  We propose a safety layer that enables a closed-form probability density/gradient of the safe generative continuous policy, end-to-end generative adversarial training, and worst-case safety guarantees. The safety layer maps all actions into a set of safe actions, and uses the change-of-variables formula plus additivity of measures for the density. In an experiment on real-world driver interaction data, we empirically demonstrate tractability, safety and imitation performance of our approach.
  arXiv  Detail & Related papers  (2022-03-03T13:03:06Z)
• Learn Zero-Constraint-Violation Policy in Model-Free Constrained Reinforcement Learning [7.138691584246846]
  We propose the safe set actor-critic (SSAC) algorithm, which confines the policy update using safety-oriented energy functions. The safety index is designed to increase rapidly for potentially dangerous actions. We claim that we can learn the energy function in a model-free manner similar to learning a value function.
  arXiv  Detail & Related papers  (2021-11-25T07:24:30Z)
• Safe Learning of Uncertain Environments for Nonlinear Control-Affine Systems [10.918870296899245]
  We consider the problem of safe learning in nonlinear control-affine systems subject to unknown additive uncertainty. We model uncertainty as a Gaussian signal and use state measurements to learn its mean and covariance bounds. We show that with an arbitrarily large probability we can guarantee that the state will remain in the safe set, while learning and control are carried out simultaneously.
  arXiv  Detail & Related papers  (2021-03-02T01:58:02Z)

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.