arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.20518cs.AIcs.MA
收藏

智能体的财富:跨开发者扩展智能体AI

The Wealth of Agents: Scaling Agentic AI Across Developers

Princeton University(普林斯顿大学);UC Berkeley(加州大学伯克利分校)

Austin W. Hanjie, Carlos E. Jimenez, Zirui Wang, Karthik Narasimhan

AI总结:

该研究提出多开发者智能体系统(MDAs),通过实证和理论模型对比发现,MDAs在GAIA基准上的表现优于单开发者智能体系统,可作为智能体AI扩展的新轴。

摘要:

如今的智能体系统通常由单个开发者设计、构建和部署,其可完全控制所有参与的智能体。虽然这简化了开发过程,但限制了智能体系统的潜在规模。我们研究多开发者智能体系统(MDAs),该系统使开发者能够协作构建智能体系统,以推动前沿能力超越任何单个开发者所能实现的水平。我们构建了开发者的实证和理论模型,以比较MDAs与单开发者智能体系统(SDAs)。在通用助手基准GAIA上,一组专业开发者的单个智能体准确率不超过35%,当这些智能体在MDA中组合时,准确率达到70%。该MDA的表现比使用数倍于每个专业开发者开发预算构建的通用SDAs的中位数高出12个百分点。我们的理论模型显示,MDAs如何能够激励专业化并鼓励更高效地利用聚合的开发者资源。综合来看,我们的结果为MDAs作为一种新的扩展轴提供了初步依据,该扩展轴使具有不同能力和资源的开发者能够协作推进智能体AI。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑