Nice!

Briefly, the idea is recursively to decompose tasks into the simplest possible steps, recursively call (relatively small) LLMs as agents to execute one step at a time, and using a clever voting scheme to choose how to execute each step. The authors use this technique to get a relatively small LLM to solve Towers of Hanoi with 20 rings (1M steps). All of it using natural language.

The most obvious question is whether other tasks, more interesting -- less "rote" -- than Towers of Hanoi, can similarly be recursively decomposed into simple steps. I'm not sure that's always possible.

> The approach relies on an extreme decomposition of a task into subtasks, each of which can be tackled by focused microagents. The high level of modularity resulting from the decomposition allows error correction to be applied at each step through an efficient multi-agent voting scheme.

Big if that the decomposition and the voting happen accurately for anything other than toy problems

Worth opening the pdf just for the graph on page 1.

And you can decompose the proof of Fermat's last theorem into logical combinators.

The meat is in decomposing the difficult problem into steps

I have ADHD and the same approach works for me. (In fact, most days it is essential!)

Here is the pseudocode of MAKER:

  state = init_state()
  while state is not complete:
    state = LLM("You are a helpful assistant. The rules and format of the game is [...]. The correct strategy to use at each step is [...]. The current state is [...]. Output the state after making the next move")

I dunno, even though the authors address its use, making the task Tower of Hanoi doesn't meet the excitement of the title.

one issue I see is when steps in a plan depend on one another, when you cannot know all the next steps exactly before seeing the results of the previous ones, when you may have to backtrack sometimes

On the surface this is an interesting concept...

The paper however, meh...

No mention of MoE. One would think this is a logical evolution of that but not a mention (that I saw). Its own rubric for the task, Towers of Hanoi, was admittedly weak.

LLM papers are starting to look like the last decade of JS frameworks and Tools. Only with less code and more academics, and thats disappointing, because I think a lack of pragmatism and grounding is now holding the field back...