CEO-Bench

CEO-Bench is a multi-agent benchmark that evaluates the decision-making capabilities of large language models (LLMs) in CEO-level strategic resource reallocation by requiring them to synthesize conflicting advice from specialized C-suite advisors within a constraint-rich organizational environment.

Papers using CEO-Bench (2)

CEO-Bench: Can Agents Play the Long Game?2026Can LLMs Be CEOs? Benchmarking Strategic Resource Reallocation with Multi-Role Agent Simulation2026