Abstract
Recent years have witnessed increasing interest in extending large language models into agentic systems. While the effectiveness of agents has continued to improve, efficiency, which is crucial for real-world deployment, has often been overlooked. This paper therefore investigates efficiency from three core components of agents: memory, tool learning, and planning, considering costs such as latency, tokens, steps, etc. Aimed at conducting comprehensive research addressing the efficiency of the agentic system itself, we review a broad range of recent approaches that differ in implementation yet frequently converge on shared high-level principles including but not limited to bounding context via compression and management, designing reinforcement learning rewards to minimize tool invocation, and employing controlled search mechanisms to enhance efficiency, which we discuss in detail. Accordingly, we characterize efficiency in two complementary ways: comparing effectiveness under a fixed cost budget, and comparing cost at a comparable level of effectiveness. This trade-off can also be viewed through the Pareto frontier between effectiveness and cost. From this perspective, we also examine efficiency oriented benchmarks by summarizing evaluation protocols for these components and consolidating commonly reported efficiency metrics from both benchmark and methodological studies. Moreover, we discuss the key challenges and future directions, with the goal of providing promising insights.
Abstract (translated)
近年来，人们对将大型语言模型扩展为代理系统表现出日益浓厚的兴趣。尽管代理的有效性一直在提高，但对效率的重视往往被忽视，而效率对于实际部署至关重要。因此，本文从三个核心组件——记忆、工具学习和规划的角度探讨了效率问题，并考虑了诸如延迟、令牌、步骤等成本因素。 为了进行全面研究以解决代理系统本身的效率问题，我们回顾了一系列近期的方法，这些方法虽然在实现上有所不同，但往往共同遵循着一些高级原则，包括但不限于通过压缩和管理来限制上下文范围，在强化学习奖励设计中最小化工具调用频率以及使用受控搜索机制提高效率。我们在文中详细讨论了这些问题。 相应地，我们将效率定义为两个互补的方式：在固定成本预算下比较效果，并在同一效果水平上比较成本。这种权衡也可以通过有效性与成本之间的帕累托前沿视角来看待。从这一角度来看，我们还研究了以这些组件的评估协议和汇总基准及方法学研究报告中常用的效率指标为基础的面向效率的基准测试。 此外，讨论关键挑战并提出未来方向的目标是为该领域提供有希望的新见解。
URL
https://arxiv.org/abs/2601.14192
