I'm going through the same problem right now

Qwen 3.8 27b is the supervisor

Qwen 3.5 4b are the 6-15 minions it controls

Gemma 4 e4b is the validator for the supervisor.

A plan means it preps all work for the agents up front, tests that evals work, makes sure the dev environment is right for each agent, then finds and fixes each before the distributed tasks even begin.

What I thought would take minutes took hours as a supervisor or one agent did the prep / pre flight work.

My solution so far has been to drop all but basic setup and force the supervisor to ask before every op - if this is not the design choices, can this be run in parallel? If so, hand it off NOW.

I'm still iterating this workflow, but less setup for all the minions plus handing them work that may be incomplete/ broken is caught and fixed by the minion and its own qa gates.

This can mean a number of minions end up replicating the same fixes, but in general the time cost of that is small Vs the supervisor working in parallel instead of too sequentially.

▲ mappu an hour ago | parent | next [-]

If you can run the smarter 3.8 27B model, why not use it for everything?

▲ adastra22 16 hours ago | parent | prev | next [-]

Tell the planner to not do all that. Just plan out the high level. No code. No implementation details.

	▲	tcdent 4 hours ago \| parent [-]
		Yeah, it's way better when you do design documentation, or even ticketing, to instruct it not to include any implementation specifics. You're not doing the deep dive on the zero shot that writes the ticket or the document and so it is much less informed than the agent doing the work will be.

▲ UncleOxidant 4 hours ago | parent | prev | next [-]

How do you set all of that up with supervisor and minions? What harness?

▲ MuffinFlavored 4 hours ago | parent | prev [-]

    > Qwen 3.8 27b is the supervisor
    > 
    > Qwen 3.5 4b are the 6-15 minions it controls
    > 
    > Gemma 4 e4b is the validator for the supervisor.

I just use Opus 5.5 and don't think about it?

▲

SillyUsername 3 hours ago | parent | next [-]

These are self hosted for learning experience, I could have built an agent swarm in the cloud, but I'd never have learnt the fundamentals.

- Cold starts impact, context length issues, task lifecycle management

- Inefficiencies in delegation, necessitating workflow patterns for small projects (big AIs hide this problem until you scale and they hit the same issues).

- Limits of the AI would be harder to find or notice (e.g. where time - and cost - is being spent needlessly).

▲

UncleOxidant 4 hours ago | parent | prev [-]

Or just use a more capable local model like Qwen3.8-Flash-Next?

	▲	solarkraft 3 hours ago \| parent [-]
		Or Kimi K3? /s Some people are resource constrained.