Multi18 Access

| Method | Avg. Reward (norm.) | Constraint Violations (%) | Cross-domain Transfer Gain | |----------|---------------------|----------------------------|----------------------------| | Mono | 0.61 | 22.1% | — | | Multi5 | 0.73 | 15.4% | +0.07 | | HRL | 0.69 | 18.9% | +0.04 | | Multi18 | | 8.3% | +0.21 |

We introduced Multi18, a framework for multi-agent coordination across 18 distinct domains. By combining per-domain specialization with a global constraint-satisfaction layer, Multi18 outperforms monolithic and lower-agent-count baselines. The design principle of choosing N based on empirical complexity bounds (here, N=18) may generalize to other “multi-N” systems in applied AI. multi18

A. Chen, B. Novak, S. Kapoor Institute for Distributed Intelligence | Method | Avg

Results (averaged over 5 seeds) :

Limitations: Multi18 assumes known domain boundaries and a static set of 18 environments. Extensions to open-ended domains (e.g., new domain appears online) remain future work. The design principle of choosing N based on