Efficient Agents: Building Effective Agents While Reducing Cost
Ningning Wang, Xavier Hu, Pai Liu, He Zhu, Yue Hou, Heyuan Huang, Shengyu Zhang, Jian Yang, Jiaheng Liu, Ge Zhang, Changwang Zhang, Jun Wang, Yuchen Eleanor Jiang, Wangchunshu Zhou

TL;DR
This paper systematically studies the efficiency-effectiveness trade-off in LLM-driven agents, proposing a new framework that maintains high performance while significantly reducing operational costs, thus enhancing scalability and accessibility.
Contribution
It introduces the Efficient Agents framework, optimizing agent complexity and design to balance performance and cost, supported by empirical analysis on the GAIA benchmark.
Findings
Efficient Agents retains 96.7% of OWL's performance.
Operational costs are reduced from $0.398 to $0.228.
Achieves a 28.4% improvement in cost-of-pass.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
