Aurora: Neuro-Symbolic AI Driven Advising Agent

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lugones, Lorena Amanda Quincoso, Kverne, Christopher, Bhimani, Nityam Sharadkumar, Oliveira, Ana Carolina, Polyzou, Agoritsa, Lisetti, Christine, Bhimani, Janki
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908843148050432
author Lugones, Lorena Amanda Quincoso
Kverne, Christopher
Bhimani, Nityam Sharadkumar
Oliveira, Ana Carolina
Polyzou, Agoritsa
Lisetti, Christine
Bhimani, Janki
author_facet Lugones, Lorena Amanda Quincoso
Kverne, Christopher
Bhimani, Nityam Sharadkumar
Oliveira, Ana Carolina
Polyzou, Agoritsa
Lisetti, Christine
Bhimani, Janki
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_17999
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Aurora: Neuro-Symbolic AI Driven Advising Agent
Lugones, Lorena Amanda Quincoso
Kverne, Christopher
Bhimani, Nityam Sharadkumar
Oliveira, Ana Carolina
Polyzou, Agoritsa
Lisetti, Christine
Bhimani, Janki
Human-Computer Interaction
Artificial Intelligence
K.3.1; I.2.4; I.2.7
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.
title Aurora: Neuro-Symbolic AI Driven Advising Agent
topic Human-Computer Interaction
Artificial Intelligence
K.3.1; I.2.4; I.2.7
url https://arxiv.org/abs/2602.17999