Efficient Agents: Building Effective Agents While Reducing Cost

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Ningning, Hu, Xavier, Liu, Pai, Zhu, He, Hou, Yue, Huang, Heyuan, Zhang, Shengyu, Yang, Jian, Liu, Jiaheng, Zhang, Ge, Zhang, Changwang, Wang, Jun, Jiang, Yuchen Eleanor, Zhou, Wangchunshu
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918114108637184
author Wang, Ningning
Hu, Xavier
Liu, Pai
Zhu, He
Hou, Yue
Huang, Heyuan
Zhang, Shengyu
Yang, Jian
Liu, Jiaheng
Zhang, Ge
Zhang, Changwang
Wang, Jun
Jiang, Yuchen Eleanor
Zhou, Wangchunshu
author_facet Wang, Ningning
Hu, Xavier
Liu, Pai
Zhu, He
Hou, Yue
Huang, Heyuan
Zhang, Shengyu
Yang, Jian
Liu, Jiaheng
Zhang, Ge
Zhang, Changwang
Wang, Jun
Jiang, Yuchen Eleanor
Zhou, Wangchunshu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_02694
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient Agents: Building Effective Agents While Reducing Cost
Wang, Ningning
Hu, Xavier
Liu, Pai
Zhu, He
Hou, Yue
Huang, Heyuan
Zhang, Shengyu
Yang, Jian
Liu, Jiaheng
Zhang, Ge
Zhang, Changwang
Wang, Jun
Jiang, Yuchen Eleanor
Zhou, Wangchunshu
Artificial Intelligence
Computation and Language
Multiagent Systems
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.
title Efficient Agents: Building Effective Agents While Reducing Cost
topic Artificial Intelligence
Computation and Language
Multiagent Systems
url https://arxiv.org/abs/2508.02694