从记忆、工具学习和规划三方面提升智能体效率，兼顾性能与成本。
Toward Efficient Agents: Memory, Tool learning, and Planning
- 通过压缩管理上下文、优化奖励减少工具调用、控制搜索提升效率。
- 提出双维度评估：固定成本下比效果，或固定效果下比成本。
- 梳理主流评测协议与效率指标，为高效智能体设计提供方向。
近年来，大语言模型向智能体系统扩展受到广泛关注。尽管智能体的有效性持续提升，但实际部署所需的效率却常被忽视。本文从智能体的三个核心组件——记忆、工具学习和规划——出发，考察延迟、令牌数、步骤数等开销。为系统研究智能体本身的效率，我们综述了近期多种实现方式各异但普遍遵循相似高层原则的方法，包括上下文压缩与管理、设计强化学习奖励以最小化工具调用、采用受控搜索机制提升效率。我们从两个互补角度刻画效率：在固定成本预算下比较有效性，或在相当有效性水平下比较成本。这一权衡可视为效果与成本间的帕累托前沿。基于此，我们总结了面向效率的评测协议，并整合基准与方法研究中常用的效率指标。最后，讨论关键挑战与未来方向，旨在提供有前景的洞察。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。