English

A Hybrid Multi-Agent Prompting Approach for Simplifying Complex Sentences

Computation and Language 2025-06-18 v2

Abstract

This paper addresses the challenge of transforming complex sentences into sequences of logical, simplified sentences while preserving semantic and logical integrity with the help of Large Language Models. We propose a hybrid approach that combines advanced prompting with multi-agent architectures to enhance the sentence simplification process. Experimental results show that our approach was able to successfully simplify 70% of the complex sentences written for video game design application. In comparison, a single-agent approach attained a 48% success rate on the same task.

Keywords

Cite

@article{arxiv.2506.11681,
  title  = {A Hybrid Multi-Agent Prompting Approach for Simplifying Complex Sentences},
  author = {Pratibha Zunjare and Michael Hsiao},
  journal= {arXiv preprint arXiv:2506.11681},
  year   = {2025}
}
R2 v1 2026-07-01T03:15:38.619Z