Co-Saving: Resource Aware Multi-Agent Collaboration for Software Development
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910971299102720 |
|---|---|
| author | Qiu, Rennai Qian, Chen Li, Ran Dang, Yufan Chen, Weize Yang, Cheng Zhang, Yingli Tian, Ye Xiong, Xuantang Han, Lei Liu, Zhiyuan Sun, Maosong |
| author_facet | Qiu, Rennai Qian, Chen Li, Ran Dang, Yufan Chen, Weize Yang, Cheng Zhang, Yingli Tian, Ye Xiong, Xuantang Han, Lei Liu, Zhiyuan Sun, Maosong |
| contents | Recent advancements in Large Language Models (LLMs) and autonomous agents have demonstrated remarkable capabilities across various domains. However, standalone agents frequently encounter limitations when handling complex tasks that demand extensive interactions and substantial computational resources. Although Multi-Agent Systems (MAS) alleviate some of these limitations through collaborative mechanisms like task decomposition, iterative communication, and role specialization, they typically remain resource-unaware, incurring significant inefficiencies due to high token consumption and excessive execution time. To address these limitations, we propose a resource-aware multi-agent system -- Co-Saving (meaning that multiple agents collaboratively engage in resource-saving activities), which leverages experiential knowledge to enhance operational efficiency and solution quality. Our key innovation is the introduction of "shortcuts" -- instructional transitions learned from historically successful trajectories -- which allows to bypass redundant reasoning agents and expedite the collective problem-solving process. Experiments for software development tasks demonstrate significant advantages over existing methods. Specifically, compared to the state-of-the-art MAS ChatDev, our method achieves an average reduction of 50.85% in token usage, and improves the overall code quality by 10.06%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_21898 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Co-Saving: Resource Aware Multi-Agent Collaboration for Software Development Qiu, Rennai Qian, Chen Li, Ran Dang, Yufan Chen, Weize Yang, Cheng Zhang, Yingli Tian, Ye Xiong, Xuantang Han, Lei Liu, Zhiyuan Sun, Maosong Computation and Language Artificial Intelligence Multiagent Systems Software Engineering Recent advancements in Large Language Models (LLMs) and autonomous agents have demonstrated remarkable capabilities across various domains. However, standalone agents frequently encounter limitations when handling complex tasks that demand extensive interactions and substantial computational resources. Although Multi-Agent Systems (MAS) alleviate some of these limitations through collaborative mechanisms like task decomposition, iterative communication, and role specialization, they typically remain resource-unaware, incurring significant inefficiencies due to high token consumption and excessive execution time. To address these limitations, we propose a resource-aware multi-agent system -- Co-Saving (meaning that multiple agents collaboratively engage in resource-saving activities), which leverages experiential knowledge to enhance operational efficiency and solution quality. Our key innovation is the introduction of "shortcuts" -- instructional transitions learned from historically successful trajectories -- which allows to bypass redundant reasoning agents and expedite the collective problem-solving process. Experiments for software development tasks demonstrate significant advantages over existing methods. Specifically, compared to the state-of-the-art MAS ChatDev, our method achieves an average reduction of 50.85% in token usage, and improves the overall code quality by 10.06%. |
| title | Co-Saving: Resource Aware Multi-Agent Collaboration for Software Development |
| topic | Computation and Language Artificial Intelligence Multiagent Systems Software Engineering |
| url | https://arxiv.org/abs/2505.21898 |