SOURCE-LINKED INTELLIGENCE

Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Prompt optimization can improve multi-agent LLM systems, but the prompts being optimized often serve two entangled roles: generating task-relevant content and specifying execution-critical protocols, such as message routing, output formatting, and termination signals, on which the underlying code relies. As a result, a prompt edit intended to improve content generation can inadvertently corrupt the protocol and cause the entire agent pipeline to fail. Our key observation is that these two roles have different representations: execution protocols are typically structured, while task-relevant co

Read original source ↗ Open in workspace

recordType

paper

region

Global