Awesome Efficient Agents: A Survey of Memory, Tool Use, and Planning

🤝 **Contributions welcome!** This repository is actively maintained and continuously updated. Feel free to open an issue or submit a pull request to add papers, fix links, or improve categorization.

⚡Introduction

Recent years have seen growing interest in extending large language models into agentic systems. While agent capabilities have advanced rapidly, efficiency has received comparatively less attention despite being crucial for real-world deployment. This repository studies efficiency-guided agent design from three core components: memory, tool use, and planning.

We provide a curated paper list to help readers quickly locate representative work, along with lightweight notes on how each topic connects to efficiency.

Efficient Memory. We organize memory-related papers into three processes: construction, management, and access.
Efficient Tool Use. We group papers into tool selection, tool calling, and tool-integrated reasoning.
Efficient Planning. We collect work on planning that improves overall agent efficiency by reducing unnecessary actions and shortening trajectories.

🧾Paper List

📂 Table of Contents(click to expand/collapse)

🧠Memory
🛠️Tool Use
🧩Planning
- Single-Agent Planning Efficiency
- Multi-Agent Collaborative Efficiency
📑Related Surveys

🧠Memory

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

Latent and Parametric Memory

Latent Memory

(2026-01) FlashMem: Distilling Intrinsic Latent Memory via Computation Reuse
(2025-09) MemGen: Weaving Generative Latent Memory for Self-Evolving Agents
(2025-02) M+: Extending MemoryLLM with Scalable Long-Term Memory
(2025-01) Titans: Learning to Memorize at Test Time
(2024-09) MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation
(2024-07) $\text{Memory}^3$: Language Modeling with Explicit Memory
(2024-02) MEMORYLLM: Towards Self-Updatable Large Language Models
(2024-01) Long Context Compression with Activation Beacon

Textual Memory

Prompt-resident Memory

Item-based Memory

Graph-based Memory

Hierarchical Memory

(2026-02) Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation
(2026-02) HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling
(2025-10) Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMs
(2025-10) LightMem: Lightweight and Efficient Memory-Augmented Generation
(2025-07) Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents
(2025-07) MemOS: A Memory OS for AI System
(2025-06) Memory OS of AI Agent
(2024-08) HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model
(2024-02) A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
(2023-10) MemGPT: Towards LLMs as Operating Systems

Procedural Reuse via Skills

Multi-Agent Memory

Shared Memory

Local Memory

Mixed Memory

🛠️Tool Use

Tool Selection

External Retriever

Multi-Label Classification (MLC)

(2024-09) Efficient and Scalable Estimation of Tool Representations in Vector Space
(2024-09) TinyAgent: Function Calling at the Edge

Vocabulary-based Retrieval

Tool Calling

In-Place Parameter Filling

(2024-01) Efficient Tool Use with Chain-of-Abstraction Reasoning
(2023-02) Toolformer: Language Models Can Teach Themselves to Use Tools

Parallel Tool Calling

(2026-02) W&D:Scaling Parallel Tool Calling for Efficient Deep Research Agents
(2024-11) CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning
(2024-05) An LLM-Tool Compiler for Fused Parallel Function Calling
(2023-12) An LLM Compiler for Parallel Function 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

🧩Planning

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

📑Related Surveys

Given that our work mainly focuses on efficiency, which is rooted in effectiveness, we’ve gathered a list of related survey papers to offer a complementary perspective. We hope this will help bring visibility to some valuable surveys that deserve more attention.💡

Memory Survey

Tool Use Survey

(2025-06) LLM-Based Agents for Tool Learning: A Survey
(2024-05) Tool Learning with Large Language Models: A Survey

Planning and Reasoning Survey

(2025-08) LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios
(2025-02) PlanGenLLMs: A Modern Survey of LLM Planning Capabilities
(2024-02) Understanding the planning of LLM agents: A survey

📌Citation

If you find this survey useful, please cite:

@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}, 
}

Name		Name	Last commit message	Last commit date
assets		assets
README.md		README.md

Latest commit

History

Folders and files

Repository files navigation