Saved in:
Bibliographic Details
Main Authors: Yang, Xiaofang, Li, Lijun, Zhou, Heng, Zhu, Tong, Qu, Xiaoye, Fan, Yuchen, Wei, Qianshan, Ye, Rui, Kang, Li, Qin, Yiran, Kou, Zhiqiang, Liu, Daizong, Li, Qi, Ding, Ning, Chen, Siheng, Shao, Jing
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.14192
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917212603809792
author Yang, Xiaofang
Li, Lijun
Zhou, Heng
Zhu, Tong
Qu, Xiaoye
Fan, Yuchen
Wei, Qianshan
Ye, Rui
Kang, Li
Qin, Yiran
Kou, Zhiqiang
Liu, Daizong
Li, Qi
Ding, Ning
Chen, Siheng
Shao, Jing
author_facet Yang, Xiaofang
Li, Lijun
Zhou, Heng
Zhu, Tong
Qu, Xiaoye
Fan, Yuchen
Wei, Qianshan
Ye, Rui
Kang, Li
Qin, Yiran
Kou, Zhiqiang
Liu, Daizong
Li, Qi
Ding, Ning
Chen, Siheng
Shao, Jing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_14192
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Toward Efficient Agents: Memory, Tool learning, and Planning
Yang, Xiaofang
Li, Lijun
Zhou, Heng
Zhu, Tong
Qu, Xiaoye
Fan, Yuchen
Wei, Qianshan
Ye, Rui
Kang, Li
Qin, Yiran
Kou, Zhiqiang
Liu, Daizong
Li, Qi
Ding, Ning
Chen, Siheng
Shao, Jing
Artificial Intelligence
Computation and Language
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.
title Toward Efficient Agents: Memory, Tool learning, and Planning
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2601.14192