arXiv cs.MA· Austin W. Hanjie, Carlos E. Jimenez, Zirui Wang, Karthik Narasimhan·· 3 天前AI 评分40
The Wealth of Agents：多开发者智能体系统如何扩展 Agentic AI
The Wealth of Agents: Scaling Agentic AI Across Developers
AI 导读
研究提出多开发者智能体系统（MDAs），让开发者协作构建智能体系统以突破单开发者（SDAs）的能力上限。在 GAIA 基准上，单个智能体准确率不超过 35% 的专业开发者群体，其智能体组合成 MDA 后达到 70%，比开发预算高出数倍的中位通用 SDA 高 12 个百分点。理论模型显示 MDAs 可激励专业化分工并更高效利用开发者资源，初步论证其作为 Agentic AI 新扩展轴的价值。
正文 · 原文
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.
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.20518 [cs.AI] |
| (or arXiv:2610.20518v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20518 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Austin W. Hanjie [view email]
[v1]
Wed, 14 Oct 2026 17:19:11 UTC (376 KB)
来源：arXiv cs.MA · arxiv.org