Anything related to reading and interpreting the environment seems to always benefit from the addition of more agents to the search party, assuming you have some rational way to synthesize their results.
Taking actions that mutate the environment is a different story. I think this is where you run into diminishing returns very quickly. You generally want one strong agent to act given the results of all the searching that was done. If the plan is clear, you don't need a genius model to execute 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.
Anything related to reading and interpreting the environment seems to always benefit from the addition of more agents to the search party, assuming you have some rational way to synthesize their results.
Taking actions that mutate the environment is a different story. I think this is where you run into diminishing returns very quickly. You generally want one strong agent to act given the results of all the searching that was done. If the plan is clear, you don't need a genius model to execute it.
I definitely think you want the genius model to synthesize everything that rolls up to them.
I think this is an unsolved problem. The most interesting thing I saw here is the Recursive Language Models paper.
https://arxiv.org/abs/2512.24601
There's also a great write up here by the author:
https://alexzhang13.github.io/blog/2025/rlm/
1 reply →
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.