AutoPR: Let's Automate Your Academic Promotion!
Qiguang Chen, Zheng Yan, Mingda Yang, Libo Qin, Yixin Yuan, Hanjing Li, Jinhao Liu, Yiyan Ji, Dengyun Peng, Jiannan Guan, Mengkang Hu, Yantao Du, Wanxiang Che
2025-10-13
Summary
This paper introduces a new idea called Automatic Promotion, or AutoPR, which aims to automatically create social media posts to help researchers share their work more effectively and get it noticed.
What's the problem?
Researchers are publishing more and more studies, and it's becoming harder to get those studies seen and used by others. Scientists spend a lot of time trying to promote their own papers on social media, which takes away from their actual research. The problem is that manually creating good social media content is time-consuming and doesn't always reach the right audience.
What's the solution?
The researchers developed a system called PRAgent that uses artificial intelligence to automatically turn research papers into engaging social media posts. PRAgent works in three steps: first, it pulls out the important information from the paper, including images and figures. Then, it uses multiple AI 'agents' to write and refine the post. Finally, it adjusts the post to fit the specific social media platform it's being shared on, like Twitter or LinkedIn, to maximize its impact. They also created a benchmark called PRBench to test how well these automated systems perform, comparing them to just using a large language model directly.
Why it matters?
This work is important because it could significantly reduce the burden on researchers to promote their own work, allowing them to focus on the science itself. The results show that PRAgent is much better at getting people to notice and engage with research papers than simply using AI to generate posts, leading to more views, likes, and overall attention. This could lead to faster scientific progress and wider impact for research findings.
Abstract
As the volume of peer-reviewed research surges, scholars increasingly rely on social platforms for discovery, while authors invest considerable effort in promoting their work to ensure visibility and citations. To streamline this process and reduce the reliance on human effort, we introduce Automatic Promotion (AutoPR), a novel task that transforms research papers into accurate, engaging, and timely public content. To enable rigorous evaluation, we release PRBench, a multimodal benchmark that links 512 peer-reviewed articles to high-quality promotional posts, assessing systems along three axes: Fidelity (accuracy and tone), Engagement (audience targeting and appeal), and Alignment (timing and channel optimization). We also introduce PRAgent, a multi-agent framework that automates AutoPR in three stages: content extraction with multimodal preparation, collaborative synthesis for polished outputs, and platform-specific adaptation to optimize norms, tone, and tagging for maximum reach. When compared to direct LLM pipelines on PRBench, PRAgent demonstrates substantial improvements, including a 604% increase in total watch time, a 438% rise in likes, and at least a 2.9x boost in overall engagement. Ablation studies show that platform modeling and targeted promotion contribute the most to these gains. Our results position AutoPR as a tractable, measurable research problem and provide a roadmap for scalable, impactful automated scholarly communication.