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.
[–] vielite1310 2 days ago
I have never see a case where I need multi-agents talking to each others or something
[–] dominotw 2 days ago
[–] bob1029 2 days ago
[–] mncharity 2 days ago
For example, a small fast model watching another model's CoT stream to annotate it - highlighting and summarizing for me, or flagging intervention conditions.
[–] gbnwl 2 days ago
[–] bob1029 2 days ago
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.
[–] mickeyp 2 days ago
Build the sub agent to your specification (prompt, how the parent agent should call it); give it tools and optionally skills; then give it permission to call some or all the other sub agents you have set up.
Easy-peasy.