Sub agents are significantly more useful than multi agents.

Wrap a nested prompt with a tool call that is invoked by the caller prompt. That is the answer to all your suffering. You can repeat this for as many layers of invocation as you desire. You can layer determinism and non-determinism as much as you like in whatever orders you see fit with additional alignment, retry policies, logging, etc.

Agents running concurrently will not go any faster than one well-designed hierarchical agent system.

Imagine the simple task of incrementing a global counter. That would be my #1 benchmark. If you can demonstrate a MAS can increment that counter faster than a single agent can (monotonically without skipping), then I will happily delete 100% of the AI-related code I've authored and start over using your ideas.

▲

gbnwl 2 hours ago | parent | next [-]

What harness are you using? In both Claude Code and Codex I run into the issue of subagents being unable to dispatch their own subagents, so I haven't been able to play with "many layers of invocation".

	▲	bob1029 44 minutes ago \| parent [-]
		Custom harness, custom tools. With custom we don't have to disclose to the caller that the implementation of the tool is another LLM. Each piece of deterministic tool code can firewall the perspective of the model as appropriate. Think of a sub agent as being isomorphic with a tool call.

▲

dominotw 2 hours ago | parent | prev | next [-]

depends on what type of problem it is

	▲	bob1029 2 hours ago \| parent [-]
		I am curious if we have any examples of problems that can only be solved via multiple concurrent prompts coordinating in real time.

▲

alala-lala-lon 2 hours ago | parent | prev [-]

[dead]