OAgents: An Empirical Study of Building Effective Agents

TL;DR

This paper conducts a systematic empirical study on agent design choices, introduces a robust evaluation protocol, and presents OAgents, a modular framework that achieves state-of-the-art performance in Agentic AI research.

Contribution

It provides a standardized evaluation protocol, analyzes the impact of design choices, and introduces OAgents, an open-source, high-performing agent framework.

Findings

Certain agent components are crucial for effectiveness.

Standardized evaluation improves reproducibility.

OAgents achieves state-of-the-art performance.

Abstract

Recently, Agentic AI has become an increasingly popular research field. However, we argue that current agent research practices lack standardization and scientific rigor, making it hard to conduct fair comparisons among methods. As a result, it is still unclear how different design choices in agent frameworks affect effectiveness, and measuring their progress remains challenging. In this work, we conduct a systematic empirical study on GAIA benchmark and BrowseComp to examine the impact of popular design choices in key agent components in a fair and rigorous manner. We find that the lack of a standard evaluation protocol makes previous works, even open-sourced ones, non-reproducible, with significant variance between random runs. Therefore, we introduce a more robust evaluation protocol to stabilize comparisons. Our study reveals which components and designs are crucial for effective agents, while others are redundant, despite seeming logical. Based on our findings, we build and open-source OAgents, a new foundation agent framework that achieves state-of-the-art performance among open-source projects. OAgents offers a modular design for various agent components, promoting future research in Agentic AI.