cd /news/ai-agents/efficient-agents · home › topics › ai-agents › article
[ARTICLE · art-148344] src=efficient-agents.github.io ↗ pub= topic=ai-agents verified=true sentiment=· neutral

Efficient Agents

A new survey paper examines efficiency in large language model agentic systems across three core components — memory, tool learning, and planning — measuring costs including latency, tokens, and steps. The paper reports that recent approaches frequently converge on shared high-level principles such as bounded context via compression and retrieval, reduced action cost via budgeted tool use and caching, and controlled search via hierarchical planning and pruning. It characterizes efficiency two ways: comparing effectiveness under a fixed cost budget and comparing cost at a comparable level of effectiveness, framed as a Pareto frontier, and consolidates efficiency metrics and benchmarks for the components.

by read11 min views1 publishedOct 9, 2026
Efficient Agents
Image: source

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 to 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 bounded context via compression and retrieval, reduced action cost via budgeted tool use and caching, and controlled search via hierarchical planning and pruning for improving 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.

Paper List Navigation #

📑 Table of Memory Contents #

In the paper, we organize memory into construction, management, and access. Since many papers overlap across these stages, this part is primarily organized around memory construction to avoid redundancy.

🔄 Working Memory #

📝 Textual Memory

🧩 Latent Memory

💾 External Memory #

📦 Item-based Memory

🕸️ Graph-based Memory

🪜 Hierarchical Memory

👥 Multi-Agent Memory #

🏠 Local Memory

🔀 Mixed Memory

📑 Table of Tool Learning Contents #

Tool Learning framework encompasses tool selection, tool calling, and tool-integrated reasoning for enhanced agent capabilities.

🔧 Tool Selection #

🔍 External Retriever

🏷️ Multi-Label Classification (MLC)

📚 Vocabulary-based Retrieval

▶️ Tool Calling #

📝 In-Place Parameter Filling

⚡ Parallel Tool Calling

💰 Cost-Aware Tool Calling

⚙️ Efficient Test-Time Scaling

🎯 Efficient Tool Calling with Post-training

🛠️ Tool-Integrated Reasoning (TIR) #

✅ Selective Invocation

🎓 Cost-Aware Policy Optimization

📑 Table of Planning Contents #

Planning framework encompasses single-agent planning efficiency and multi-agent collaborative strategies for enhanced decision-making.

🤖 Single-Agent Planning Efficiency #

💰 Adaptive Budgeting and Control

🔍 Structured Search

📋 Task Decomposition

🎯 Policy Optimization

🧠 Memory and Skill Acquisition

👥 Multi-Agent Collaborative Efficiency #

🕸️ Topological Efficiency and Sparsification

⚙️ Protocol and Context Optimization

📊 Distilling Coordination into Planning

BibTeX #

@misc{yang2026efficientagentsmemorytool,
      title={Toward Efficient Agents: Memory, Tool learning, and Planning}, 
      author={Xiaofang Yang and Lijun Li and Heng Zhou and Tong Zhu and Xiaoye Qu and Yuchen Fan and Qianshan Wei and Rui Ye and Li Kang and Yiran Qin and Zhiqiang Kou and Daizong Liu and Qi Li and Ning Ding and Siheng Chen and Jing Shao},
      year={2026},
      eprint={2601.14192},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2601.14192}, 
}
source & further reading
efficient-agents.github.io — original article
── more in #ai-agents 4 stories · sorted by recency
── more on @agentfold 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/efficient-agents] indexed:0 read:11min 2026-10-09 · —