AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Replay-Gated Neural Execution: Decoupling Persistent Behavioral Specifications from Neural Realizations in Frozen Language Models

arXiv · AI, language, vision and robotics · article · Sep 5, 2026 · UTC

Input-conditioned neural interventions raise a runtime question: what persists when one behavioral specification admits multiple actions whose validity depends on execution state? We introduce replay-gated neural execution, separating five objects: a persistent behavioral predicate, its state-indexed certified realization set, a transient action witness, a budget-limited finder, and execution authorization. Candidates undergo isolated FP32/BF16 replay of the frozen model; commitment additionally requires a valid run audit. Experiments on Qwen3-0.6B and SmolLM2-360M-Instruct establish distinct

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-25T18:52:32.462Z. This is not the publication date.