I do not understand the value of multi agent approach? Isn't a single agent with a good harness better than any multi agent env?
I do not understand the value of multi agent approach? Isn't a single agent with a good harness better than any multi agent env?
It helps you spend more token, is more expensive, and thus is obviously more AI. Also novelty and more complexity means less scrutiny of the approach.
These are necessary and perfectly sufficient for an investment firm thesis I believe.
If it's a single agent then people will just call it a chatgpt wrapper, can't have that can we
Modularity maybe. Remember, agents are basically workflows that call LLMs in certain nodes.