Multi18 Direct

The “multi” prefix in AI often implies flexibility, but most multi-agent systems are tuned for 2–5 specific domains. We ask: Can a single architecture gracefully handle 18 qualitatively different environments without retraining? The number 18 arises naturally in certain industrial settings: 18 major languages, 18 time zones, 18 sub-components of a complex supply chain. We introduce Multi18—a proof-of-concept system where 18 specialized agents share a common communication protocol and a dynamic resource allocation mechanism.

Multi18’s advantage was most pronounced in domains 14–18 (high regulatory strictness), where the arbiter prevented 94% of violations without aggressive reward shaping.

| 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 | multi18

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 Scalable Framework for Cross-Domain Multi-Agent Coordination in 18-Dimensional Constraint Spaces The “multi” prefix in AI often implies flexibility,

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. Reward (norm

Removing the coordination graph (i.e., independent agents) increased constraint violations to 27.4%, confirming the need for resource-aware arbitration. Reducing the context embedding to 8 dimensions hurt performance in the 10 text-based tasks (drop to 0.71 normalized reward), suggesting that 18 is a meaningful granularity for the tested diversity.