Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929525638561792 |
|---|---|
| author | Zhang, Guibin Yue, Yanwei Li, Zhixun Yun, Sukwon Wan, Guancheng Wang, Kun Cheng, Dawei Yu, Jeffrey Xu Chen, Tianlong |
| author_facet | Zhang, Guibin Yue, Yanwei Li, Zhixun Yun, Sukwon Wan, Guancheng Wang, Kun Cheng, Dawei Yu, Jeffrey Xu Chen, Tianlong |
| contents | Recent advancements in large language model (LLM)-powered agents have shown that collective intelligence can significantly outperform individual capabilities, largely attributed to the meticulously designed inter-agent communication topologies. Though impressive in performance, existing multi-agent pipelines inherently introduce substantial token overhead, as well as increased economic costs, which pose challenges for their large-scale deployments. In response to this challenge, we propose an economical, simple, and robust multi-agent communication framework, termed $\texttt{AgentPrune}$, which can seamlessly integrate into mainstream multi-agent systems and prunes redundant or even malicious communication messages. Technically, $\texttt{AgentPrune}$ is the first to identify and formally define the \textit{communication redundancy} issue present in current LLM-based multi-agent pipelines, and efficiently performs one-shot pruning on the spatial-temporal message-passing graph, yielding a token-economic and high-performing communication topology. Extensive experiments across six benchmarks demonstrate that $\texttt{AgentPrune}$ \textbf{(I)} achieves comparable results as state-of-the-art topologies at merely $\$5.6$ cost compared to their $\$43.7$, \textbf{(II)} integrates seamlessly into existing multi-agent frameworks with $28.1\%\sim72.8\%\downarrow$ token reduction, and \textbf{(III)} successfully defend against two types of agent-based adversarial attacks with $3.5\%\sim10.8\%\uparrow$ performance boost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_02506 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems Zhang, Guibin Yue, Yanwei Li, Zhixun Yun, Sukwon Wan, Guancheng Wang, Kun Cheng, Dawei Yu, Jeffrey Xu Chen, Tianlong Multiagent Systems Machine Learning Recent advancements in large language model (LLM)-powered agents have shown that collective intelligence can significantly outperform individual capabilities, largely attributed to the meticulously designed inter-agent communication topologies. Though impressive in performance, existing multi-agent pipelines inherently introduce substantial token overhead, as well as increased economic costs, which pose challenges for their large-scale deployments. In response to this challenge, we propose an economical, simple, and robust multi-agent communication framework, termed $\texttt{AgentPrune}$, which can seamlessly integrate into mainstream multi-agent systems and prunes redundant or even malicious communication messages. Technically, $\texttt{AgentPrune}$ is the first to identify and formally define the \textit{communication redundancy} issue present in current LLM-based multi-agent pipelines, and efficiently performs one-shot pruning on the spatial-temporal message-passing graph, yielding a token-economic and high-performing communication topology. Extensive experiments across six benchmarks demonstrate that $\texttt{AgentPrune}$ \textbf{(I)} achieves comparable results as state-of-the-art topologies at merely $\$5.6$ cost compared to their $\$43.7$, \textbf{(II)} integrates seamlessly into existing multi-agent frameworks with $28.1\%\sim72.8\%\downarrow$ token reduction, and \textbf{(III)} successfully defend against two types of agent-based adversarial attacks with $3.5\%\sim10.8\%\uparrow$ performance boost. |
| title | Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems |
| topic | Multiagent Systems Machine Learning |
| url | https://arxiv.org/abs/2410.02506 |