I used this architecture for a while. The problem I have with it is that starting from one agent and fanning out keeps things mostly aligned with that single reasoning trajectory, even as you get a few layers into the stack. Every recursive invocation is a product of the caller's current state. Diversity doesn't really occur on its own unless the environment (tool calling) is complex/chaotic.
RLM might be more useful on the execution side than on the research side. In fact, these somehow feel like they might be exact inverses of each other in terms of what the ideal architecture looks like. At some point you definitely do need something in the middle that has it all sorted out.
Yeah, a lot of people have reported significant gains from "model fusion" lately, which I think the literature just calls ensembles. You just ask a bunch of models to do a thing and then you combine the results.
Research tasks benefit the most from this. Because such work benefits from having a large number of agents working on a problem in parallel (i.e. crawling the web), and the model size becomes less important past a certain minimum.
I don't know about other categories of work, like programming. I imagine looking for bugs or security issues would benefit from it.
This is why in your brain you have trillion threads processing and summarizing sensor data (immutable functions), but a SINGLE thread of “execution” which we call the conscious soul.
https://arxiv.org/abs/2512.24601
There's also a great write up here by the author:
https://alexzhang13.github.io/blog/2025/rlm/