TopoDIM: One-shot Topology Generation of Diverse Interaction Modes for Multi-Agent Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911597048365056 |
|---|---|
| author | Sun, Rui Ding, Jie Gong, Chenghua Gu, Tianjun Jiang, Yihang Zhang, Juyuan Pan, Liming Lü, Linyuan |
| author_facet | Sun, Rui Ding, Jie Gong, Chenghua Gu, Tianjun Jiang, Yihang Zhang, Juyuan Pan, Liming Lü, Linyuan |
| contents | Optimizing communication topology in LLM-based multi-agent system is critical for enabling collective intelligence. Existing methods mainly rely on spatio-temporal interaction paradigms, where the sequential execution of multi-round dialogues incurs high latency and computation. Motivated by the recent insights that evaluation and debate mechanisms can improve problem-solving in multi-agent systems, we propose TopoDIM, a framework for one-shot Topology generation with Diverse Interaction Modes. Designed for decentralized execution to enhance adaptability and privacy, TopoDIM enables agents to autonomously construct heterogeneous communication without iterative coordination, achieving token efficiency and improved task performance. Experiments demonstrate that TopoDIM reduces total token consumption by 46.41% while improving average performance by 1.50% over state-of-the-art methods. Moreover, the framework exhibits strong adaptability in organizing communication among heterogeneous agents. Code is available at: https://github.com/Sundiasy/TopoDIM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_10120 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TopoDIM: One-shot Topology Generation of Diverse Interaction Modes for Multi-Agent Systems Sun, Rui Ding, Jie Gong, Chenghua Gu, Tianjun Jiang, Yihang Zhang, Juyuan Pan, Liming Lü, Linyuan Multiagent Systems Artificial Intelligence Computation and Language Optimizing communication topology in LLM-based multi-agent system is critical for enabling collective intelligence. Existing methods mainly rely on spatio-temporal interaction paradigms, where the sequential execution of multi-round dialogues incurs high latency and computation. Motivated by the recent insights that evaluation and debate mechanisms can improve problem-solving in multi-agent systems, we propose TopoDIM, a framework for one-shot Topology generation with Diverse Interaction Modes. Designed for decentralized execution to enhance adaptability and privacy, TopoDIM enables agents to autonomously construct heterogeneous communication without iterative coordination, achieving token efficiency and improved task performance. Experiments demonstrate that TopoDIM reduces total token consumption by 46.41% while improving average performance by 1.50% over state-of-the-art methods. Moreover, the framework exhibits strong adaptability in organizing communication among heterogeneous agents. Code is available at: https://github.com/Sundiasy/TopoDIM. |
| title | TopoDIM: One-shot Topology Generation of Diverse Interaction Modes for Multi-Agent Systems |
| topic | Multiagent Systems Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2601.10120 |