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: instead of 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 carries a natural‑language instruction describing the message the source agent should provide to the target agent.
The compiled temporal graph is then executed via structured message passing: a controller assigns neighbors to each agent, agents update their reasoning states by integrating their previous states with messages from assigned neighbors, and a final aggregator synthesizes the resulting states into the answer. This design separates graph compilation from execution, making multi‑agent coordination explicit, inspectable, and task‑conditioned without requiring reinforcement learning or gradient‑based topology optimization.
Across knowledge reasoning, mathematical problem solving, code generation, and GAIA‑style assistant tasks, ReActNet consistently outperforms fixed‑topology and learned‑topology baselines while maintaining competitive inference cost. These results suggest that effective multi‑agent orchestration depends not only on which agents communicate, but also on engineering executable workflow graphs that encode when, why, and how information should flow during reasoning.
Review