Aurora: Neuro-Symbolic AI Driven Advising Agent

Lorena Amanda Quincoso Lugones; Christopher Kverne; Nityam Sharadkumar Bhimani; Ana Carolina Oliveira; Agoritsa Polyzou; Christine Lisetti; Janki Bhimani

cs.HCFeb 20, 2026

Aurora: Neuro-Symbolic AI Driven Advising Agent

Authors: Lorena Amanda Quincoso Lugones, Christopher Kverne, Nityam Sharadkumar Bhimani, Ana Carolina Oliveira, Agoritsa Polyzou, Christine Lisetti, Janki Bhimani

Organizations: Florida International University Miami, FL, United States · Northeastern University Boston, MA, United States

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.

Figures & tables

Figure 1. Aurora system overview. Green = knowledge base; blue = neuro-symbolic reasoning; red = Chain-of-Thought prompt segment. Solid arrows denote data flow; dashed line box show control or context boundaries.

Figure 2. Conceptual ER diagram. Purple = entities; green = relationships. Connectivity encoded in three types of links: 0..* ( e.g., a course can cover zero or many skills); 1..* (e.g., a program-offering may include at least one course); 1..1 (e.g., every program-offering is tied to exactly one major).

Category	Persona	Sample Query
Short-term (Next Term)	CS Major	What courses should I take next semester to stay on track for my CS-BS degree?
Long-term (Degree Plan)	CS Major	Plan the rest of my CS-BS degree so I can graduate on time.
Skill-aligned	CS Major	I’d like an AI-oriented schedule for next Fall. What should I take?
Short-term (Next Term)	CS Minor	Please suggest my next-term schedule to finish the CS minor (12-credit cap).
Out-of-scope	CS Major	What can I do if a class is difficult?

Table 1. Representative evaluation queries.

Panel of Figure 3 — Figure 3. Per-query cosine similarity averaged over five runs.

Educational Technology

Educational technology studies digital tools and systems that support teaching, learning, assessment, and educational decision-making.

See all 118 papers

Carolina Guide: A Multi-Agent RAG System with Institutional Guardrails for Academic Policy Assistance
Jun 11, 2026Ben Torsion, Jun ZhouMulti-Agent LLM Systems LLM Guardrails
University of South Carolina, Columbia, South Carolina, USA · University of South Carolina, Columbia, USA
Deterministic Decisions for High-Stakes AI. A Zero-Egress Pipeline with the Deployability of RAG and the Accuracy of Machine Learning
Jun 28, 2026Craig AtkinsonAI in Education LLM Decision-Making
Verificate Pty Ltd, Sydney, Australia
A Hybrid AI Framework for Academic Advising: Integrating Ensemble-Based Grade Prediction and a Rule-Based Expert System
Aug 12, 2026Hamid Saadatfar, Rohollah Hedayati-Nasab, AmirHossein Eshghi +1Educational Technology Educational Data Mining
Associate Professor, Department of Computer Engineering, Faculty of Electrical and Computer Engineering, University of Birjand, Birjand, Iran. · Visiting Lecturer and IT Specialist, Department of Computer Engineering, Faculty of Electrical and Computer Engineering, University of Birjand, Birjand, Iran. · Msc Student, Department of Computer Engineering, Faculty of Electrical and Computer Engineering, University of Birjand, Birjand, Iran.

Jun 11, 2026J/K move · Enter open · S save

Carolina Guide: A Multi-Agent RAG System with Institutional Guardrails for Academic Policy Assistance

Ben Torsion, Jun Zhou

University of South Carolina, Columbia, South Carolina, USA · University of South Carolina, Columbia, USA

Multi-Agent LLM Systems LLM Guardrails Agentic RAG RAG Evaluation

Open paper AskPDF arXiv

University students often struggle to navigate complex academic policies, leading to advising bottlenecks and delayed access to critical information. Although large language models (LLMs) offer promise for automated assistance, their tendency toward hallucination and inability to enforce institutional constraints make them unsuitable for high-stakes policy guidance without careful architectural design. We present Carolina Guide, a retrieval-augmented generation (RAG) system for academic policy assistance at the University of South Carolina (USC). The system employs a modular multi-agent pipeline with institutional guardrails to provide citation-supported, policy-grounded answers to student queries while refusing unsafe requests such as course recommendations or personalized advising. We evaluate the system on a 90 query test set across 6 departments, achieving 98.9% retrieval success at the >= 2 threshold (genuinely relevant results) with the first relevant chunk at rank-1 for 98.9% of queries (MRR at 10 for rel >= 2 = 0.989). Through systematic baseline comparisons and ablation studies, we show that each architectural component-MMR reranking, adequate retrieval context (k=20), and citation enforcement-contributes measurable practical value despite limited statistical power at 90 queries. The evaluation of the guardrail on 30 adversarial queries demonstrates Safety F1 of 0.89, correctly refusing 86% of unsafe queries while maintaining 93% coverage of benign queries. These results show that production-ready LLM systems for institutional policy guidance require rethinking standard RAG patterns to prioritize safety, transparency, and departmental autonomy over conversational sophistication.

Abstract

Educational Technology

Explore similar work

Carolina Guide: A Multi-Agent RAG System with Institutional Guardrails for Academic Policy Assistance

Deterministic Decisions for High-Stakes AI. A Zero-Egress Pipeline with the Deployability of RAG and the Accuracy of Machine Learning

A Hybrid AI Framework for Academic Advising: Integrating Ensemble-Based Grade Prediction and a Rule-Based Expert System