STORM: AI Agents for Long-Form Writing

Writing a well-structured and organized piece of content is crucial for effectively conveying information to readers. One of the key elements in achieving this is the use of top-down approach for writing, i.e, nailing down the outline before writing a single word. They provide a framework that guides the writer in presenting information in a logical and coherent manner.

In this blog post, we will explore an agentic system called STORM, which stands for Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking. STORM is designed to assist in writing long-form articles by creating topic outlines, discovering diverse perspectives and simulating conversations with topic experts.

STORM can enhance the pre-writing stage, resulting in well-structured and comprehensive articles that rival those found on Wikipedia.

What is STORM?

STORM stands for Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking. It is an agentic system that assists in generating topic outlines for writing Wikipedia-like articles. STORM aims to automate the pre-writing stage by leveraging large language models (LLMs) and simulating conversations between writers and topic experts.

One of the key features of STORM is its ability to discover diverse perspectives in researching a given topic. By considering multiple viewpoints, STORM helps writers develop a well-rounded understanding of the subject matter, leading to more comprehensive and informative articles .

Another important capability of STORM is its simulation of conversations where writers carrying different perspectives pose questions to a topic expert. This multi-perspective question asking allows writers to delve deeper into the topic and formulate in-depth questions through iterative research.

Overall, STORM provides a systematic approach to the pre-writing stage, helping users research the topic, gather diverse perspectives, and formulate insightful questions. By automating these steps, STORM enables creation of grounded and organized long-form articles with comparable breadth and depth to Wikipedia pages.

How does STORM work?

The STORM process can be broken down into three main steps: retrieval, multi-perspective question asking, and synthesis. The following diagram provides an illustration of the process.

Curious to delve deeper into this?

Join Professor Mehdi as he delves into the STORM technique, considerations for production, in the video below!👇

Subscribe to Our YouTube Channel!

We are kicking off our YouTube channel in the new year, and we invite you on board as we walk you through some of these intricacies about AI, fueled by the feedback from our readers, friends and colleagues!

We want to make our channel about AI for everyone. Similar to this newsletter, we’ll talk about new AI products, the latest trends, the nitty-gritty engineering stuff, career insights for AI enthusiasts, and, of course, one of our favorite topics – the entrepreneurial side of AI - 🥳

we're here to show you how you can ride the AI wave and be your own entrepreneur using the cool tools available in the market.

---

🛠️✨ Happy practicing and happy building! 🚀🌟

Thanks for reading our newsletter. You can follow us here: Angelina Linkedin or Twitter and Mehdi Linkedin or Twitter.

Source of images/quotes:

🗞️Paper: Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models: https://arxiv.org/pdf/2402.14207.pdf

📚 Also if you'd like to learn more about RAG systems, check out our book on the RAG system:

📬 Don't miss out on the latest updates - Subscribe to our newsletter: