Multi-agent systems
How populations of learning agents cooperate, compete, and coordinate, and what shapes the outcomes they reach.
- Corresponding Researcher
- Matija Franklin
- Relevant for
- 3 cells in the AGI institutions grid
- Contact
- multi-agent@agi-institutions.org
Selected papers
6
In a swarm of 100 research agents, an exploit spread through shared tools and a counter-movement of whistleblowers emerged; proposes Ostrom-style commons governance for agent collectives.
Identifies environments in which individually capable agents can become locked into collectively harmful patterns of interaction.
Examines why intelligence developed without social interaction may not acquire the capacities needed for robust cooperation.
Frames the distribution of benefits, risks, and decision power as a central part of AGI safety rather than a downstream policy question.
Studies economies populated by AI agents and the institutional questions created by machine-speed exchange and coordination.
Builds agents that infer obligative and prohibitive norms from observed compliance, letting groups converge on shared institutions such as resource management and compensation rules.
Work in the field
10
Background work
4
Older work the field builds on, often from outside it.