Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Survey and paper list on efficiency-guided LLM agents (memory, tool use, planning).
| Date | Stars |
|---|---|
| 2026-07-31 | 290 |
| 2026-08-06 | 290 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<h1 align="center">Awesome Efficient Agents: A Survey of Memory, Tool Use, and Planning</h1>
<div align="center">
<a href="https://arxiv.org/abs/2601.14192"><img src="https://img.shields.io/badge/arXiv-2601.14192-b31b1b.svg?logo=arxiv" alt="arXiv"></a>
<a href="https://efficient-agents.github.io/"><img src="https://img.shields.io/badge/Project%20Page-efficient--agents.github.io-1E88E5.svg?logo=googlehome&logoColor=1E88E5" alt="Project Page"></a>
<a href="https://huggingface.co/papers/2601.14192"><img src="https://img.shields.io/badge/Hugging%20Face-Paper-ffcc4d.svg?logo=huggingface" alt="Hugging Face Paper"></a>
</div>
🤝 **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
<details open>
<summary>📂 Table of Contents<em>(click to expand/collapse)</em></summary>
<ul>
<li><a href="#memory">🧠Memory</a>
<ul>
<li><a href="#latent-and-parametric-memory">Latent and Parametric Memory</a>
<ul>
<li><a href="#latent-memory">Latent Memory</a></li>
<li><a href="#parametric-memory">Parametric Memory</a></li>
</ul>
</li>
<li><a href="#textual-memory">Textual Memory</a>
<ul>
<li><a href="#prompt-resident-memory">Prompt-resident Memory</a></li>
<li><a href="#item-based-memory">Item-based Memory</a></li>
<li><a href="#graph-based-memory">Graph-based Memory</a></li>
<li><a href="#hierarchical-memory">Hierarchical Memory</a></li>
</ul>
</li>
<li><a href="#skills">Procedural Reuse via Skills</a>
<li><a href="#multi-agent-memory">Multi-Agent Memory</a>
<ul>
<li><a href="#shared-memory">Shared Memory</a></li>
<li><a href="#local-memory">Local Memory</a></li>
<li><a href="#mixed-memory">Mixed Memory</a></li>
</ul>
</li>
</ul>
</li>
<li><a href="#tool-use">🛠️Tool Use</a>
<ul>
<li><a href="#tool-selection">Tool Selection</a>
<ul>
<li><a href="#external-retriever">External Retriever</a></li>
<li><a href="#multi-label-classification-mlc">Multi-Label Classification (MLC)</a></li>
<li><a href="#vocabulary-based-retrieval">Vocabulary-based Retrieval</a></li>
</ul>
</li>
<li><a href="#tool-calling">Tool Calling</a>
<ul>
<li><a href="#in-place-parameter-filling">In-Place Parameter Filling</a></li>
<li><a href="#parallel-tool-calling">Parallel Tool Calling</a></li>
<li><a href="#cost-aware-tool-calling">Cost-Aware Tool Calling</a></li>
<li><a href="#efficient-test-time-scaling">Efficient Test-Time Scaling</a></li>
<li><a href="#efficient-tool-calling-with-post-trainingExcerpt of 59,891 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:94ccfe5b96a4eed7, topic:awesome, desc:paper list