Efficient Agents: Building Effective Agents While Reducing Cost
Abstract
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 0.228, 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.
Cite
@article{arxiv.2508.02694,
title = {Efficient Agents: Building Effective Agents While Reducing Cost},
author = {Ningning Wang and Xavier Hu and Pai Liu and He Zhu and Yue Hou and Heyuan Huang and Shengyu Zhang and Jian Yang and Jiaheng Liu and Ge Zhang and Changwang Zhang and Jun Wang and Yuchen Eleanor Jiang and Wangchunshu Zhou},
journal= {arXiv preprint arXiv:2508.02694},
year = {2025}
}
Comments
Work in progress. For GitHub repository, see https://github.com/OPPO-PersonalAI/OAgents