Which Rules Matter Now? Policy-Centroid Routing Before an Intelligent System Acts

arXiv:2608.30757 · cs.AI, cs.CY · Submitted 2026-08-31 · Read on arXiv

cs.AI, cs.CY

Submitted: 2026-08-31

Updated: 2026-08-31

Comments: Theory and research-program paper; 9 pages, 1 figure, 2 tables. Includes a synthetic worked example; reports no empirical efficacy result

Code: https://github.com/SRFPBC/policy-centroid-routing

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

Abstention — 5× in this paper · explained in 1 episode
Cosine Similarity — 3× in this paper · explained in 3 episodes
AI Agents — 2× in this paper · explained in 2 episodes
Adaptation — 2× in this paper · explained in 1 episode
Few-Shot Learning — 2× in this paper · explained in 4 episodes
Actor — 1× in this paper · explained in 3 episodes
Allocator — 1× in this paper · explained in 1 episode
Calibration — 1× in this paper · explained in 7 episodes
Concept Drift — 1× in this paper · explained in 4 episodes
Core — 1× in this paper · explained in 2 episodes
Cross-lingual Transfer — 1× in this paper · explained in 2 episodes
Information Leakage — 1× in this paper · explained in 2 episodes
Online Adaptation — 1× in this paper · explained in 3 episodes
Open Security Controls Assessment Language — 1× in this paper
Verification — 1× in this paper · explained in 2 episodes
Xtensible Access Control Markup Language — 1× in this paper

Sources

Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Related papers