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

TL;DR

This paper introduces Co-Saving, a resource-aware multi-agent system that uses learned shortcuts to reduce token usage and improve code quality in software development tasks, addressing inefficiencies in existing multi-agent systems.

Contribution

The paper presents a novel resource-aware multi-agent framework with learned shortcuts to enhance efficiency and solution quality in collaborative tasks.

Findings

50.85% reduction in token usage compared to ChatDev

10.06% improvement in code quality

Effective resource savings in software development tasks

Abstract

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%.