SOURCE-LINKED INTELLIGENCE

Inference-Time Graph Engineering for Multi-Agent LLM Workflows

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

Recent multi-agent LLM systems increasingly rely on graph-structured communication to coordinate specialized agents. We revisit multi-agent orchestration from a graph-engineering perspective: rather than optimizing a static topology, we synthesize a task-conditioned temporal workflow graph that jointly specifies agent connectivity and edge-level communication semantics. We introduce ReActNet, a training-free framework that compiles a query and a set of role-specialized agents into a sequence of directed communication graphs. Each graph snapshot corresponds to one reasoning stage, and each edge

Read original source ↗ Open in workspace

recordType

paper

region

Global