Collaborative agent systems outperform solo developers in accuracy
The Wealth of Agents: Scaling Agentic AI Across Developers
Artificial IntelligenceMultiagent Systems
Summary
Building AI systems with multiple developers working together can create better performing agents than those made by individuals working alone. The authors found that when specialized developers combine their efforts, their overall system can be much more accurate. Their models show that collaboration encourages developers to focus on their strengths and use resources more efficiently. This suggests that teamwork in AI development can push capabilities beyond what single developers can achieve.
What this means in practice
- •For software development teams: Build complex AI assistants by combining specialists’ efforts to exceed single-developer system accuracy.
- •For ai platform providers: Create tools that enable multiple developers to collaboratively develop and deploy agentic AI systems efficiently.$Commercial implications: Enables platforms offering multi-developer AI collaboration tools that boost AI assistant performance and developer productivity.
Authors
Austin W. Hanjie, Carlos E. Jimenez, Zirui Wang, Karthik Narasimhan
Abstract
Today's agentic systems are typically designed, built, and deployed by single developers with full control over all participating agents. While this simplifies development, it limits the potential scale of agentic systems. We study multi-developer agentic systems (MDAs) which enable developers to collaboratively build agentic systems to push frontier capability beyond what any individual developer could achieve alone. We construct empirical and theoretical models of developers to compare MDAs with single-developer agentic systems (SDAs). On GAIA, a general assistant benchmark, a population of specialized developers whose individual agents do not exceed 35% accuracy reaches 70% when their agents are combined in an MDA. This MDA performs 12 percentage points above the median general-purpose SDA built with several times each specialist's development budget. Our theoretical models show how MDAs can incentivize specialization and encourage more efficient use of aggregated developer resources. Put together, our results make a preliminary case for MDAs as a new scaling axis by enabling developers with diverse capabilities and resources to advance agentic AI collaboratively.