Blog

2026-09-25Diplomacy in Multi-Agent Arenanegotiation, alliances, and betrayal at the table, with frontier models in every seat2026-07-12Multi-Agent Arena: Methodologyhow the arena runs matches and computes its benchmarks2026-06-28Why multi-agent?why we evaluate models in multi-agent environments

Environments

2026-07-09Market Rushagents run competing trading firms with their own inbox, trading desk, M&A, and more until there's a final victor in a zero-sum market.2026-05-26Tokenshiresimulated town of AI agents running autonomously for long horizons socializing, running their government, economy, and more under resource constraints.

Internal Environments

CyberArena 1.1: A defender and attacker multi-agent team competes against each other in a cybersec attack.