TodyComm: Task-Oriented Dynamic Communication for Multi-Round LLM-based Multi-Agent System

TL;DR

TodyComm introduces a dynamic, task-oriented communication algorithm for multi-round multi-agent systems, adapting topologies across rounds to improve task performance under varying conditions.

Contribution

It proposes a novel adaptive communication method that adjusts topologies dynamically, enhancing multi-agent collaboration in changing environments.

Findings

Outperforms fixed topology methods on five benchmarks.

Achieves better task utility under adversarial and bandwidth constraints.

Maintains token efficiency, scalability, and generalizability.

Abstract

Multi-round LLM-based multi-agent systems rely on effective communication structures to support collaboration across rounds. However, most existing methods employ a fixed communication topology during inference, which falls short in many realistic applications where the agents' roles may change \textit{across rounds} due to dynamic adversary, task progression, or time-varying constraints such as communication bandwidth. In this paper, we propose addressing this issue through TodyComm, a \textbf{t}ask-\textbf{o}riented \textbf{dy}namic \textbf{comm}unication algorithm. It produces behavior-driven collaboration topologies that adapt to the dynamics at each round, optimizing the utility for the task through policy gradient. Experiments on five benchmarks demonstrate that, under both dynamic adversarial settings and communication budget constraints, TodyComm achieves superior task performance while maintaining token efficiency, scalability, and strong generalizability across varying adversarial conditions.