迈向高效智能体：记忆、工具学习与规划

摘要

近年来，将大型语言模型扩展为智能体系统的研究日益受到关注。尽管智能体的效能持续提升，但对其实际部署至关重要的效率问题却常被忽视。为此，本文从智能体的三个核心组件——记忆、工具学习与规划入手，结合延迟、令牌消耗、步骤数等成本指标，系统性地探讨效率优化问题。通过审视大量近期研究，我们发现不同实现方法虽各有差异，却常遵循共同的高层原则：包括但不限于通过压缩与管理技术限制上下文长度、设计强化学习奖励函数以最小化工具调用次数、采用受控搜索机制提升效率等。基于此，我们提出两种互补的效率评估方式：在固定成本预算下比较效能表现，以及在同等效能水平下比较成本消耗。这种权衡关系亦可从效能与成本的帕累托前沿视角加以理解。在此基础上，我们通过归纳各组件的评估范式、整合基准测试与方法论研究中常用效率指标，系统梳理了面向效率的评估体系。最后，本文讨论了当前面临的关键挑战与未来研究方向，以期为该领域提供有价值的见解。

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.

迈向高效智能体：记忆、工具学习与规划

Toward Efficient Agents: Memory, Tool learning, and Planning

摘要

Support