Policy-Governed LLM Routing with Intent Matching for Instrument Laboratories
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 35 references that are in the map. First posted on arXiv 3 Apr 2026.
Builds on
13 of 35 references.
References · 13
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
- 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
- 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
- 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 682
- 2024Unifying AI Tutor Evaluation: An Evaluation Taxonomy for Pedagogical Ability Assessment of LLM-Powered AI Tutorscited by 61
- 2025Training LLM-based Tutors to Improve Student Learning Outcomes in Dialoguescited by 43
- 2025Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)cited by 19
- 2025ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queriescited by 14
- 2024RNR: Teaching Large Language Models to Follow Roles and Rulescited by 6
- 2025One Head, Many Models: Cross-Attention Routing for Cost-Aware LLM Selectioncited by 4
1 more
Built on by
Not cited yet.