A novel is basically like a software project, it requires multiple specialized parties and extensive planning.
Agent 1 : writing the draft (will likely be of poor quality)
Agent 2 : fleshing out or adding characters
Agent 3 : giving flavor to the writing style
Agent 4 : verifying inconsistencies
etc.
I’m working on a project that intends to solve that issue/do that work (though not using agents, essentially by training custom models with the ability to do “recursive”/in-depth work). The example I give in the docs is for a dissertation, but future plans are to enable something like a novel (in particular by implementing a memory system).
The project: https://github.com/arthurwolf/llmi/blob/main/README.md