CLAIMASEMay 28, 2025

Co-Saving: Resource Aware Multi-Agent Collaboration for Software Development

arXiv:2505.21898v14 citationsh-index: 11
Originality Incremental advance
AI Analysis

This addresses resource inefficiencies in multi-agent collaboration for software development, offering a domain-specific incremental improvement.

The paper tackles the inefficiency of multi-agent systems in software development by proposing Co-Saving, a resource-aware approach that uses learned shortcuts to reduce token usage by 50.85% and improve code quality by 10.06% compared to ChatDev.

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%.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes