Machine Heart

Jul 6, 2026 · Artificial Intelligence

Evaluating Multi-Agent LLM Systems: Rethinking the Orchestrator’s Role

The paper reveals that failures in LLM‑driven multi‑agent systems often stem from the Orchestrator’s loss of control, introduces an entropy‑dynamics framework to measure scheduling entropy, and proposes Inverse Workflow Generation for detailed process evaluation, shifting focus from agent strength to orchestration stability.