TRACE-CS: A Hybrid Logic-LLM System for Explainable Course Scheduling

Stylianos Loukas Vasileiou, William Yeoh
9/5/2024
cs.AI

No official code found. Best implementation: YODA-Lab/TRACE-CS (6 stars, last commit 2026-02-22).

Abstract

We present TRACE-CS, a novel hybrid system that combines symbolic reasoning with large language models (LLMs)to address contrastive queries in course scheduling problems. TRACE-CS leverages logic-based techniques to encode scheduling constraints and generate provably correct explanations, while utilizing an LLM to process natural language queries and refine logical explanations into user friendly responses. This system showcases how combining symbolic KR methods with LLMs creates explainable AI agents that balance logical correctness with natural language accessibility, addressing a fundamental challenge in deployed scheduling systems.

View on arXivView PDF

Code Implementations(1)

YODA-Lab/TRACE-CSCommunity100%

Trustworthy Reasoning for Contrastive Explanations in Course Scheduling Problems (Demo)

61PythonAug 29, 20248 months ago

Similar Papers

ChatLogic: Integrating Logic Programming with Large Language Models for Multi-Step Reasoning

81% match1 repo162024

Non-Interactive Symbolic-Aided Chain-of-Thought for Logical Reasoning

79% match2025

Improved Logical Reasoning of Language Models via Differentiable Symbolic Programming

79% match1 repo132023

From Language to Logic: A Bi-Level Framework for Structured Reasoning

79% match2025

Delta1 with LLM: symbolic and neural integration for credible and explainable reasoning

79% match2026

Teaching LLMs to Think Mathematically: A Critical Study of Decision-Making via Optimization

79% match2025

Cite this paper

@article{vasileiou2024tracecs,
  title  = {TRACE-CS: A Hybrid Logic-LLM System for Explainable Course Scheduling},
  author = {Stylianos Loukas Vasileiou and William Yeoh},
  year   = {2024},
  eprint = {2409.03671},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2409.03671v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2409.03671.svg)](https://codeofpaper.com/paper/2409.03671)

Discussion