高效智能体：在降低成本的同时构建高效能代理

摘要

大型语言模型（LLM）驱动代理的卓越能力，使得复杂系统能够应对多步骤任务，但其不断攀升的成本威胁着系统的可扩展性和可访问性。本研究首次系统性地探讨了现代代理系统中效率与效能之间的权衡，旨在满足在不牺牲性能的前提下实现成本效益设计的迫切需求。我们探究了三个关键问题：（1）代理任务本质上需要多少复杂度？（2）何时额外模块的加入会带来收益递减？（3）通过设计高效代理框架，能在多大程度上提升效率？基于GAIA基准的实证分析，我们评估了LLM主干选择、代理框架设计及测试时扩展策略的影响。采用“通过成本”指标，我们量化了这些维度上的效率-性能权衡。研究结果指导了“高效代理”这一新型代理框架的开发，该框架具备与任务需求相匹配的最优复杂度。高效代理在保持开源领先代理框架OWL 96.7%性能的同时，将运营成本从0.398降至0.228，实现了通过成本28.4%的提升。我们的工作为设计高效、高性能的代理系统提供了可操作的见解，推动了AI驱动解决方案的可访问性与可持续性发展。

English

The remarkable capabilities of Large Language Model (LLM)-driven agents have enabled sophisticated systems to tackle complex, multi-step tasks, but their escalating costs threaten scalability and accessibility. This work presents the first systematic study of the efficiency-effectiveness trade-off in modern agent systems, addressing the critical need for cost-effective designs without sacrificing performance. We investigate three key questions: (1) How much complexity do agentic tasks inherently require? (2) When do additional modules yield diminishing returns? (3) How much efficiency can be gained through the design of efficient agent frameworks? Through an empirical analysis on the GAIA benchmark, we evaluate the impact of LLM backbone selection, agent framework designs, and test-time scaling strategies. Using the cost-of-pass metric, we quantify the efficiency-performance trade-off across these dimensions. Our findings inform the development of Efficient Agents , a novel agent framework that has an optimal complexity to task requirements. Efficient Agents retains 96.7% of the performance of OWL, one leading open-source agent framework, while reducing operational costs from 0.398 to 0.228, resulting in a 28.4% improvement in cost-of-pass. Our work provides actionable insights for designing efficient, high-performing agent systems, advancing the accessibility and sustainability of AI-driven solutions.

高效智能体：在降低成本的同时构建高效能代理

Efficient Agents: Building Effective Agents While Reducing Cost

摘要

Support