Aurora: Neuro-Symbolic AI Driven Advising Agent

2026-02-20

AI Summary

This study addresses the challenge posed by excessively high student-to-faculty ratios—often exceeding 300:1—in higher education, which impedes timely, compliant, and personalized academic advising, thereby increasing the risk of delayed graduation and exacerbating educational inequity. To mitigate this, the authors propose a modular neuro-symbolic system that uniquely integrates a Boyce-Codd Normal Form (BCNF)-compliant course rulebase, a Prolog-based symbolic reasoning engine, and an instruction-tuned large language model augmented with retrieval-augmented generation (RAG). The resulting framework delivers highly accurate, interpretable, and traceable advising decisions, demonstrating robust performance in edge cases: semantic alignment improves from 0.68 to 0.93, nearly half of all scenarios achieve perfect precision and recall, unanswerable queries are correctly deferred, and average response time is reduced to just 0.71 seconds—83 times faster than baseline methods.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Cognitive Modeling & Cognitive Systems: Symbolic Representations
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Academic advising in higher education is under severe strain, with advisor-to-student ratios commonly exceeding 300:1. These structural bottlenecks limit timely access to guidance, increase the risk of delayed graduation, and contribute to inequities in student support. We introduce Aurora, a modular neuro-symbolic advising agent that unifies retrieval-augmented generation (RAG), symbolic reasoning, and normalized curricular databases to deliver policy-compliant, verifiable recommendations at scale. Aurora integrates three components: (i) a Boyce-Codd Normal Form (BCNF) catalog schema for consistent program rules, (ii) a Prolog engine for prerequisite and credit enforcement, and (iii) an instruction-tuned large language model for natural-language explanations of its recommendations. To assess performance, we design a structured evaluation suite spanning common and edge-case advising scenarios, including short-term scheduling, long-term roadmapping, skill-aligned pathways, and out-of-scope requests. Across this diverse set, Aurora improves semantic alignment with expert-crafted answers from 0.68 (Raw LLM baseline) to 0.93 (+36%), achieves perfect precision and recall in nearly half of in-scope cases, and consistently produces correct fallbacks for unanswerable prompts. On commodity hardware, Aurora delivers sub-second mean latency (0.71s across 20 queries), approximately 83X faster than a Raw LLM baseline (59.2s). By combining symbolic rigor with neural fluency, Aurora advances a paradigm for accurate, explainable, and scalable AI-driven advising.

Problem

• academic advising
• advisor-to-student ratio
• student support inequity
• timely guidance
• delayed graduation

Innovation

• neuro-symbolic AI
• retrieval-augmented generation
• symbolic reasoning
• academic advising
• explainable AI