# GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems

arXiv: https://arxiv.org/abs/2603.19677 · HTML: https://mlsanity.com/paper/2603.19677/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 27 of its 43 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 27 of 27)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems](https://mlsanity.com/paper/1705.04146/) (2017)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [Solving General Arithmetic Word Problems](https://mlsanity.com/paper/1608.01413/) (2016)
- [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024)
- [Hierarchical Generation of Molecular Graphs using Structural Motifs](https://mlsanity.com/paper/2002.03230/) (2020)
- [Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://mlsanity.com/paper/2406.02818/) (2024)
- [Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies](https://mlsanity.com/paper/2502.02533/) (2025)
- [Learning Efficient Multi-agent Communication: An Information Bottleneck Approach](https://mlsanity.com/paper/1911.06992/) (2019)
- [Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation](https://mlsanity.com/paper/2507.18224/) (2025)
- [Learning Multi-Agent Communication from Graph Modeling Perspective](https://mlsanity.com/paper/2405.08550/) (2024)
- [Graph Diffusion Transformers for Multi-Conditional Molecular Generation](https://mlsanity.com/paper/2401.13858/) (2024)
- [Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2505.23352/) (2025)
- [GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modeling](https://mlsanity.com/paper/2505.19234/) (2025)
- [Social learning strategies modify the effect of network structure on group performance](https://mlsanity.com/paper/1606.00753/) (2016)
- [Using Motif Transitions for Temporal Graph Generation](https://mlsanity.com/paper/2306.11190/) (2023)
- [Benefits and Limitations of Communication in Multi-Agent Reasoning](https://mlsanity.com/paper/2510.13903/) (2025)
- [Scalable Temporal Motif Densest Subnetwork Discovery](https://mlsanity.com/paper/2406.10608/) (2024)
- [ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies](https://mlsanity.com/paper/2602.14681/) (2026)

## Built on by (most cited first, 5 of 5)

- [Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.29790/) (2026)
- [Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspective](https://mlsanity.com/paper/2608.18104/) (2026)
- [Roles with Rails: Contract-Preserving Role Evolution in Multi-Agent Structured Reasoning](https://mlsanity.com/paper/2605.28433/) (2026)
- [OpenMAS-GCom. A Diagnostic Benchmark for Graph-enhanced Multi-Agent Systems](https://mlsanity.com/paper/2609.21527/) (2026)
- [MAGIC: Mixed-Granularity Agent Graphs via Incremental Construction with Dense-Reward Reinforcement Learning](https://mlsanity.com/paper/2609.26667/) (2026)

## Abstract (arXiv)

Large language model (LLM)-based multi-agent systems (MAS) have demonstrated exceptional capabilities in solving complex tasks, yet their effectiveness depends heavily on the underlying communication topology that coordinates agent interactions. Within these systems, successful problem-solving often necessitates task-specific group structures to divide and conquer subtasks. However, most existing approaches generate communication topologies in a node-centric manner, leaving group structures to emerge implicitly from local connectivity decisions rather than modeling them explicitly, often leading to suboptimal coordination and unnecessary communication overhead. To address this limitation, we propose GoAgent (Group-of-Agents), a communication topology generation method that explicitly treats collaborative groups as the atomic units of MAS construction. Specifically, GoAgent first enumerates task-relevant candidate groups through an LLM and then autoregressively selects and connects these groups as atomic units to construct the final communication graph, jointly capturing intra-group cohesion and inter-group coordination. To mitigate communication redundancy and noise propagation inherent in expanding topologies, we further introduce a conditional information bottleneck (CIB) objective that compresses inter-group communication, preserving task-relevant signals while filtering out redundant historical noise. Extensive experiments on six benchmarks demonstrate the state-of-the-art performance of GoAgent with 93.84% average accuracy while reducing token consumption by about 17%.