AI-Press: A Multi-Agent News Generating and Feedback Simulation System Powered by Large Language Models
Xiawei Liu, Shiyue Yang, Xinnong Zhang, Haoyu Kuang, Libo Sun, Yihang Yang, Siming Chen, Xuanjing Huang, Zhongyu Wei
TL;DR
This paper addresses the challenge of reliable, ethics-aware news generation by integrating multi-agent collaboration with Retrieval-Augmented Generation (RAG) and a demographic-aware feedback simulation. AI-Press partitions the workflow into drafting, polishing, and simulation modules, employing Searchers, Writers, Reviewers, and Rewriters to produce high-quality, publishable news content and to anticipate audience reactions. Through extensive experiments across genres and a simulation study grounded in real-world demographic data, the framework shows improvements over prompt-only baselines and demonstrates that demographic distributions shape and predict public feedback with high fidelity. The work offers a practical, human-in-the-loop approach to faster, safer, and more targeted news production and audience modeling, with potential impact on editorial decision-making and platform-level content strategy.
Abstract
The rise of various social platforms has transformed journalism. The growing demand for news content has led to the increased use of large language models (LLMs) in news production due to their speed and cost-effectiveness. However, LLMs still encounter limitations in professionalism and ethical judgment in news generation. Additionally, predicting public feedback is usually difficult before news is released. To tackle these challenges, we introduce AI-Press, an automated news drafting and polishing system based on multi-agent collaboration and Retrieval-Augmented Generation. We develop a feedback simulation system that generates public feedback considering demographic distributions. Through extensive quantitative and qualitative evaluations, our system shows significant improvements in news-generating capabilities and verifies the effectiveness of public feedback simulation.