Not without some significant changes in how we turn natural language into programs. Yes, you can use an agent to do it, but the agent is going to rely on a compiler for the same reason human programs do: to check semantic correctness. In theory you could build an agent that outputs machine code, but the results would be pretty terrible.

I am not sure we actually want natural language to be compiled directly to machine code anyway. Those rich type systems that Haskell people get excited about are actually automatic proof checkers, similar to Lean, and having an agent check its output against such type checkers greatly improves the code generated by agents. If anything, we will probably see more widespread use of the lambda cube type systems (with extensions e.g. double negative elimination) as agents become a standard programming tool; human beings tend to find such type systems very tedious and difficult to work with, but agents are good at dealing with tedious tasks.