Reinforcement Learning–Based Discrete Prompt Optimization for Neuro-Symbolic Structured Simplification of Complex Game Descriptions with Large Language Models

This thesis investigates how large language models can be trained to perform structured simplification of complex, free-form game descriptions for the GameChangineer platform. The work formalizes simplification as a discrete prompt optimization problem and introduces a neuro-symbolic pipeline that maps raw natural language into controlled GameChangineer sentences via scenario normalization, retrieval-augmented code generation, and AST-based FACTS extraction. A reinforcement learning framework based on Proximal Policy Optimization optimizes discrete prompt edits using task-specific rewards that combine grammar compliance, semantic agreement with the FACTS contract, and compiler validity of the resulting games. Experiments on diverse arcade-style game descriptions show that the proposed GC-Repair and sentence correction agents significantly improve grammar-constrained generation, robustness to noisy user input, and end-to-end code correctness compared to direct LLM rewriting baselines.

Name thesis:degree_name

Master of Science

Level thesis:degree_level

masters

Discipline thesis:degree_discipline

Computer Engineering

Department dc:contributor.department

Electrical and Computer Engineering

Grantor dc:publisher

Virginia Tech

Year dc:date.issued

2026

Author dc:creator

• Bhatt, Shubham Satyaprakash

Chairs dc:contributor.committeechair

• Hsiao, Michael S.
• Abbott, Amos L.

Committee member dc:contributor.committeemember

• Wang, Yue J.

• Text Simplification
• Neuro-Symbolic NLP
• Retrieval-Augmented Generation
• Reinforcement Learning
• Controlled Natural Language

Statement dc:rights

• In Copyright

Licence dc:rights.uri

• http://rightsstatements.org/vocab/InC/1.0/

Language dc:language.iso

en

Dc Identifier Other

vt_gsexam:45464

OAI identifier oai:identifier

oai:vtechworks.lib.vt.edu:10919/140897