邁向高效能智能體：記憶、工具學習與規劃

摘要

近年來，將大型語言模型擴展為智能體系統的研究日益受到關注。儘管智能體的效能持續提升，但對實際部署至關重要的效率問題卻常被忽視。本文因此從智能體的三個核心組件——記憶、工具學習與規劃——切入探討效率議題，並考量延遲、標記數、步驟數等成本因素。為對智能體系統本身的效率進行全面性研究，我們回顧了大量近期研究方法：這些方法在實作層面雖有差異，卻常遵循共同的高階原則（包括但不限於透過壓縮與管理來限制上下文、設計強化學習獎勵以最小化工具調用、採用受控搜索機制提升效率），本文將對此展開詳細討論。據此，我們以兩種互補方式界定效率：在固定成本預算下比較效能，以及在相當效能水平下比較成本。此權衡關係亦可透過效能與成本間的帕雷托前沿來觀察。基於此視角，我們透過彙整這些組件的評估流程，並統整基準測試與方法論研究中常見的效率指標，進一步檢視以效率為導向的基準測試。此外，我們探討關鍵挑戰與未來方向，以期提供具前瞻性的見解。

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.

邁向高效能智能體：記憶、工具學習與規劃

Toward Efficient Agents: Memory, Tool learning, and Planning

摘要

Support