高效能代理：在降低成本的同時構建有效代理

摘要

大型語言模型（LLM）驅動的代理展現了卓越的能力，使複雜的多步驟任務得以由精密的系統處理，但其不斷攀升的成本威脅著可擴展性和可及性。本研究首次系統性地探討了現代代理系統中效率與效能之間的權衡，回應了在不犧牲性能的前提下設計成本效益系統的迫切需求。我們探討了三個關鍵問題：(1) 代理任務本質上需要多少複雜性？(2) 何時額外的模組會導致收益遞減？(3) 通過設計高效的代理框架，能獲得多少效率提升？基於GAIA基準的實證分析，我們評估了LLM骨幹選擇、代理框架設計以及測試時擴展策略的影響。利用「通過成本」指標，我們量化了這些維度上的效率與效能權衡。我們的研究成果啟發了「高效代理」的開發，這是一種新穎的代理框架，其複雜性與任務需求達到最佳匹配。高效代理保留了領先開源代理框架OWL 96.7%的性能，同時將運營成本從0.398降低至0.228，使通過成本提升了28.4%。我們的工作為設計高效且高性能的代理系統提供了可操作的見解，推動了AI驅動解決方案的可及性與永續性發展。

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.

高效能代理：在降低成本的同時構建有效代理

Efficient Agents: Building Effective Agents While Reducing Cost

摘要

Support