Metaintelligence architectureMetaintelligence · Topology · Self-organisation

Living graph: topology shaped by work

An architecture diagram goes out of date the moment it is drawn. A living graph tries to close the gap between the diagram and the system: links here are not designed in advance. They arise from the participants’ local decisions and disappear when they stop being useful.

Metaintelligence architecture · part 4 of 6

One round of evolution

The system’s structure is rebuilt continuously, and every cycle consists of the same steps. Only steps linked as cause and effect run one after another. Everything else runs in parallel.

  1. A participant publishes an advertisement with a limited lifetime: what it accepts, what it produces, what it needs and how many more links it can take on.
  2. Every other participant independently scores the visible candidates by its own criteria.
  3. The pair negotiates in alternating moves: proposal, counter-proposal, agreement or refusal.
  4. A link on probation comes into being.
  5. The boundaries are synchronised in parallel with the system’s other links.
  6. The link’s strength and reliability are updated from the actual result.
  7. The parties review the terms: strengthen, weaken, put to sleep, dissolve.

Why topology is not assigned from above

The environment gives participants a way to meet but leaves the choice to them. The reason is practical. To choose the best structure centrally, you need to know the state of all participants at once. That is either expensive or inaccurate: while the state is being collected, it is already changing.

Local decisions do not produce the best structure. They produce a workable one that keeps adjusting. We assume that over the long run this is worth more than a one-off best structure for conditions that have already moved on. Only experiments can test that assumption.

What you see when you watch it

When you run such a system and watch it over time, some characteristic things show up:

These are observations from our runs, not proven laws. The one thing we have measured rigorously so far argues against big conclusions: in a comparison with 16 agents and five seeds, the graph of links gave no advantage, 97.21% of tasks completed successfully against 97.24% without the graph, and the sign of the difference changed from seed to seed. The tasks there were single-agent, so whether a living graph helps where joint work is needed remains an open question.

Where a living graph is not needed

What this changes in how you think

The least familiar part here is giving up the question “which architecture is right”. In its place comes the question “which environment rules lead to the behaviour we need”. This is closer to designing an economy or the rules of a game than to drawing a flowchart: you set constraints and incentives, and the system finds the structure itself.

Hence the way to check it. The question is “what happened in the run”, not “does the system match the diagram”. A separate part of the series covers reproducible runs and evidence.

Code and artefacts

The “Metaintelligence architecture” series

  1. Metaintelligence: why the environment around the model sets a system’s ceiling
  2. The agent as a bounded local world
  3. A link as a first-class object: a relationship with state and history
  4. Living graph: topology shaped by work
  5. Consensus without a centre: deciding together without taking anyone’s word for it
  6. Agent economics: autonomy needs a budget

Frequently asked questions

How do you debug a system whose structure keeps changing?

Through events. Every change in topology (an advertisement, a proposal, an agreement, a revision, a link falling asleep) is recorded. You debug from the reconstructed history of a specific run; a diagram is not needed for that.

Will self-organisation not lead to chaos?

The environment sets the constraints: a participant’s link capacity, the cost of exchange, the lifetime of advertisements, probation for new links. Chaos arises where everything is free. In a bounded environment, useless activity does not pay for itself.

Can part of the structure be fixed?

Yes, and in practice that is what is done: critical links are set rigidly, while the adaptive part stays alive. The mixed mode is usually the one that works. A fully self-organising system is interesting for research, but a product rarely needs it as a whole.

How we help with this

Read next

Follow the series

If you’re building a similar environment or want to discuss the research with us, write through the form on the homepage.

Email hello@xteam.pro