TodyComm: Task-Oriented Dynamic Communication for Multi-Round LLM-based Multi-Agent System
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909032511438848 |
|---|---|
| author | Fan, Wenzhe Tognoli, Tommaso Zou, Henry Peng Miao, Chunyu Wang, Yibo Zhang, Xinhua |
| author_facet | Fan, Wenzhe Tognoli, Tommaso Zou, Henry Peng Miao, Chunyu Wang, Yibo Zhang, Xinhua |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03688 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TodyComm: Task-Oriented Dynamic Communication for Multi-Round LLM-based Multi-Agent System Fan, Wenzhe Tognoli, Tommaso Zou, Henry Peng Miao, Chunyu Wang, Yibo Zhang, Xinhua Artificial Intelligence 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. |
| title | TodyComm: Task-Oriented Dynamic Communication for Multi-Round LLM-based Multi-Agent System |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2602.03688 |