How Multiple AI Agents Will Work Together to Write Student (and Professional) Papers in the Fall
A substantial amount of the Guidance for educators being issued by various states continues to massively underestimate the power of the AI technology that is being released and is in the pipeline.
We only have to look at Andrew Ng’s recent Newsletter from today to see what is already in the works, and will almost certainly be available on a widespread basis by the fall.
From Andrew Ng’s Newsletter today:
Today, we mostly use LLMs in zero-shot mode, prompting a model to generate final output token by token without revising its work. This is akin to asking someone to compose an essay from start to finish, typing straight through with no backspacing allowed, and expecting a high-quality result. Despite the difficulty, LLMs do amazingly well at this task!
With an agent workflow, however, we can ask the LLM to iterate over a document many times. For example, it might take a sequence of steps such as:
Plan an outline.
Decide what, if any, web searches are needed to gather more information.
Write a first draft.
Read over the first draft to spot unjustified arguments or extraneous information.
Revise the draft taking into account any weaknesses spotted.
And so on.
This iterative process is critical for most human writers to write good text. With AI, such an iterative workflow yields much better results than writing in a single pass.
…
Open-source agent tools and the academic literature on agents are proliferating, making this an exciting time but also a confusing one. To help put this work into perspective, I’d like to share a framework for categorizing design patterns for building agents. My team AI Fund is successfully using these patterns in many applications, and I hope you find them useful.
Reflection: The LLM examines its own work to come up with ways to improve it.
Tool use: The LLM is given tools such as web search, code execution, or any other function to help it gather information, take action, or process data.
Planning: The LLM comes up with, and executes, a multistep plan to achieve a goal (for example, writing an outline for an essay, then doing online research, then writing a draft, and so on).
Multi-agent collaboration: More than one AI agent work together, splitting up tasks and discussing and debating ideas, to come up with better solutions than a single agent would.
Imagine that the last agent rewrites the paper in the student’s own voice, tosses in a few speeeelllinggg and grammerr errors, and makes sure it gets 5% or less on a writing detector before giving it to the student to submit.
On a positive note, how could your school use this to its advantage in the fall?