# Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems > Source: > Published: 2026-09-07 10:00:18+00:00 Multi-agent LLM systems commonly use an orchestrator to decompose a task for a team of workers and then improve through textual reflection. Despite strong empirical results, these systems lack a unified account of coordination, memory improvement, and the role of external verification. We model orch