Policy-Governed LLM Routing with Intent Matching for Instrument Laboratories

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Olowe, Emmanuel A., Chitnis, Danial
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918474759012352
author Olowe, Emmanuel A.
Chitnis, Danial
author_facet Olowe, Emmanuel A.
Chitnis, Danial
contents AI tutoring systems in engineering labs face a tension between providing sufficient assistance and preserving learning opportunities. Existing systems typically offer instructors limited control over assistance timing, content, or cost. This paper describes a routing and governance system for LLM-based lab assistance comprising two components: Routiium, an OpenAI-compatible gateway that manages multiple LLM backends with configurable prompt modifications and usage logging, and EduRouter, a policy-aware routing service that enforces per-lab budgets, approval workflows, and embedding-based question matching. We evaluated the system using trace-driven simulation calibrated from two engineering labs (LED characterization, RC circuit analysis) and a 100-query replay through live models. In simulations, governed policies (P1/P2) increased challenge-alignment index from 0.90 to 0.98 and overlay-adherence score from 0.69 to 0.87 compared to ungoverned operation (P0). The productive-struggle window metric increased from 1.4 to 3.6 simulated turns before high-scaffold hints appeared. In the 100-query replay, EduRouter routed 75% of queries to a local model, reducing token costs by 66% ($0.087 vs. $0.26 for all-premium routing) while maintaining canonical hit rate of 1.0 for the curated 89-intent question bank. We release Routiium, EduRouter, canonical-task tooling, and simulator configurations to support replication and future classroom studies.
format Preprint
id arxiv_https___arxiv_org_abs_2604_26955
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Policy-Governed LLM Routing with Intent Matching for Instrument Laboratories
Olowe, Emmanuel A.
Chitnis, Danial
Computers and Society
Artificial Intelligence
AI tutoring systems in engineering labs face a tension between providing sufficient assistance and preserving learning opportunities. Existing systems typically offer instructors limited control over assistance timing, content, or cost. This paper describes a routing and governance system for LLM-based lab assistance comprising two components: Routiium, an OpenAI-compatible gateway that manages multiple LLM backends with configurable prompt modifications and usage logging, and EduRouter, a policy-aware routing service that enforces per-lab budgets, approval workflows, and embedding-based question matching. We evaluated the system using trace-driven simulation calibrated from two engineering labs (LED characterization, RC circuit analysis) and a 100-query replay through live models. In simulations, governed policies (P1/P2) increased challenge-alignment index from 0.90 to 0.98 and overlay-adherence score from 0.69 to 0.87 compared to ungoverned operation (P0). The productive-struggle window metric increased from 1.4 to 3.6 simulated turns before high-scaffold hints appeared. In the 100-query replay, EduRouter routed 75% of queries to a local model, reducing token costs by 66% ($0.087 vs. $0.26 for all-premium routing) while maintaining canonical hit rate of 1.0 for the curated 89-intent question bank. We release Routiium, EduRouter, canonical-task tooling, and simulator configurations to support replication and future classroom studies.
title Policy-Governed LLM Routing with Intent Matching for Instrument Laboratories
topic Computers and Society
Artificial Intelligence
url https://arxiv.org/abs/2604.26955