AgentsNet

# AgentsNet

This repository contains the graph instances used in the [AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs](https://huggingface.co/papers/2507.08616) paper.

AgentsNet is a new benchmark for multi-agent reasoning, designed to measure the ability of multi-agent systems to collaboratively form strategies for problem-solving, self-organization, and effective communication given a network topology. It draws inspiration from classical problems in distributed systems and graph theory.

* **Paper**: [AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs](https://huggingface.co/papers/2507.08616)
* **Project Page**: [https://agentsnet.graphben.ch](https://agentsnet.graphben.ch)
* **GitHub Repository**: [https://github.com/ashleve/lightning-hydra-template](https://github.com/ashleve/lightning-hydra-template)

## Dataset

The dataset consists of synthetic graphs generated using various random graph models. It serves as the input for all experiments in the benchmark.

## Citation

If you use this dataset, please cite the associated paper:

```bibtex
@misc{grötschla2025agentsnetcoordinationcollaborativereasoning,
title={AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs},
author={Florian Grötschla and Luis Müller and Jan Tönshoff and Mikhail Galkin and Bryan Perozzi},
year={2025},
eprint={2507.08616},
archivePrefix={arXiv},
primaryClass={cs.MA},
url={https://arxiv.org/abs/2507.08616},
}
```

# AgentsNet
本仓库收录了论文《AgentsNet：多智能体大语言模型中的协调与协同推理》（https://huggingface.co/papers/2507.08616）中使用的各类图实例。

AgentsNet是一款全新的多智能体推理基准测试集，旨在评估多智能体系统在给定网络拓扑结构的前提下，协同制定问题求解策略、实现自组织以及开展高效沟通的能力。该基准的设计灵感来源于分布式系统与图论中的经典问题。

* **论文**：[《AgentsNet：多智能体大语言模型中的协调与协同推理》](https://huggingface.co/papers/2507.08616)
* **项目主页**：[https://agentsnet.graphben.ch](https://agentsnet.graphben.ch)
* **GitHub仓库**：[https://github.com/ashleve/lightning-hydra-template](https://github.com/ashleve/lightning-hydra-template)

## 数据集
本数据集包含通过多种随机图模型生成的合成图，可作为该基准测试集所有实验的输入数据。

## 引用
若使用本数据集，请引用以下相关论文：

bibtex
@misc{grötschla2025agentsnetcoordinationcollaborativereasoning,
title={AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs},
author={Florian Grötschla and Luis Müller and Jan Tönshoff and Mikhail Galkin and Bryan Perozzi},
year={2025},
eprint={2507.08616},
archivePrefix={arXiv},
primaryClass={cs.MA},
url={https://arxiv.org/abs/2507.08616},
}