arXiv:2607. 00044v1 Announce Type: cross Abstract: We study a finite-state symbolic controller for systems in which the admissible visible transitions are fixed in advance and each visible state carries a minimum dwell requirement.
arXiv:2608. 15976v1 Announce Type: new Abstract: A learning system can occupy execution states that are indistinguishable under every declared present-behavior readout yet respond differently to future training.
A learning system can occupy execution states that are indistinguishable under every declared present-behavior readout yet respond differently to future training. We formalize this through fiber fingerprints: controlled future-learning response laws restricted to present-behavior equivalence classes.
arXiv:2607. 29496v1 Announce Type: new Abstract: We study transcript management for fixed, finite-precision causal Transformers.
arXiv:2607. 27132v1 Announce Type: new Abstract: An agent acting under partial observability must retain a recursively updateable statistic of history that restores the Markov property, but the smallest such statistic is generally unknown.
arXiv:2608. 01548v3 Announce Type: replace Abstract: Test-time emergence in LLM systems has a deployment boundary: additional computation can realize decisions already supported by the deployed information--execution structure, while evidence, tools, memory, and executable semantics can change the class inherited by later computation.
The paper introduces topological necessities—mechanism‑invariant subgoals derived from the topology of successful trajectories—used to guide long‑horizon goal‑conditioned reinforcement learning. By computing homology in dimensions 0 and 1 over a transport‑weighted carrier, the authors obtain an enumerable gate set that forms a recursive topological gate hierarchy. These certified gates transfer across different embodiments (e.g., from PointMaze to Ant and Humanoid) without retraining, achieving state‑of‑the‑art performance on several benchmark tasks.
arXiv:2512. 18471v2 Announce Type: replace Abstract: Continual learning systems face a fundamental geometric obstacle: as experience accumulates on a fixed-capacity manifold, covering numbers grow linearly with time, eventually forcing representational overlap and catastrophic interference.
arXiv:2608. 10172v1 Announce Type: new Abstract: Mechanistic interpretability explains models by identifying circuits inside them, but has no way to tell whether a circuit is a property of the model or an artifact of the method that found it.
arXiv:2606. 16329v1 Announce Type: new Abstract: In this paper, we present a procedure for numeric planning based on Symbolic Pattern Planning (SPP).
The paper introduces a unified branch‑and‑bound framework for the Steiner Traveling Salesman Problem on Graphs of Convex Sets (GCS), where the goal is to find a minimum‑cost closed walk through required convex sets while allowing optional vertices and revisits. The method uses additive lower‑bound graph costs for committed prefixes and a cut‑separated connected‑flow relaxation for the remaining cost, guaranteeing finite termination under a uniform positive‑cost assumption. Experiments on benchmark instances show that both best‑first and depth‑first traversal strategies find feasible solutions within 30 seconds, achieving mean certified optimality gaps of 28.1% and 29.7% respectively, outperforming two recent baselines.
arXiv:2609. 11326v2 Announce Type: replace-cross Abstract: We ask whether it can be certified algorithmically that a self-modifying computational system preserves a safety property at its next step (preservation) and along its whole evolution (persistence).
arXiv:2609. 16298v1 Announce Type: new Abstract: Despite recent advances in the verification of nonlinear neural feedback systems, scalability remains the central obstacle, as state-of-the-art solvers do not yet handle the network sizes and nonlinear dynamics of autonomy applications.