MAKER System Solves Million-Step LLM Task with Zero Errors Through Extreme Decomposition

LLMs have achieved remarkable breakthroughs in reasoning, insights, and tool use, but chaining these abilities into extended processes at the scale of those routinely executed by humans, organizations, and societies has remained out of reach.

This paper describes MAKER, the first system that successfully solves a task with over one million LLM steps with zero errors, and, in principle, scales far beyond this level.

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.

Thus, the results suggest that instead of relying on continual improvement of current LLMs, massively decomposed agentic processes (MDAPs) may provide a way to efficiently solve problems at the level of organizations and societies.