Multi-agent systems: behaviour between the agents
When several agents work on one task, the result depends on how they coordinate. Failure can emerge from the interaction even when every single agent behaves as designed.
We test the interaction: message protocols, role boundaries, shared memory, and the paths by which one agent can instruct another. The interesting failures are usually coordination failures rather than model failures.
One recurring pattern is the confused deputy: an agent that holds permissions is asked to act by another that has none. Another is instruction propagation through shared files, where a rule written for one agent is followed by all of them.
We record the scenario, the configuration and the trace. A finding without a trace is a hypothesis, and we do not publish hypotheses as results.