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.
😎 A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, Agent, and Beyond
| Date | Stars |
|---|---|
| 2026-07-31 | 357 |
| 2026-08-06 | 357 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> # A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, Agent, and Beyond [](https://arxiv.org/pdf/2503.21614) [](https://mp.weixin.qq.com/s/JfXG93uOt_lTAs1zECsEsw) [](https://x.com/suzhaochen0110/status/1905461785693749709?s=46) [](https://github.com/XiaoYee/Awesome_Efficient_LRM_Reasoning) [](https://opensource.org/licenses/MIT)  </div> --- ## 🔔 News - [2026-01] Welcome to our latest survey paper "[Toward Efficient Agents: A Survey of Memory, Tool learning, and Planning](https://github.com/yxf203/Awesome-Efficient-Agents)". **Efficient reasoning** is important for building efficient agents. - [2025-12] We have **updated recent RL papers for efficient reasoning in our survey paper**. Welcome to our v2 version "[A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond](https://arxiv.org/abs/2503.21614)". - [2025-09] Welcome to our latest survey paper "[A Survey of Reinforcement Learning for Large Reasoning Models](https://github.com/TsinghuaC3I/Awesome-RL-for-LRMs)". **Efficient reasoning** is important for Reinforcement Learning of Large Reasoning Models. - [2025-08] Welcome to our latest survey paper "[Speed Always Wins: A Survey on Efficient Architectures for Large Language Models](https://github.com/weigao266/Awesome-Efficient-Arch?tab=readme-ov-file)". **Efficient architectures** are natural for achieving efficient reasoning. - [2025-07] Welcome to our latest paper "[SafeWork-R1: Coevolving Safety and Intelligence under the AI-45 Law](https://arxiv.org/pdf/2507.18576v3)". Efficient reasoning is important for **model safety** and building trustworthy models. - [2025-06] Welcome to our latest papers "[OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning](https://github.com/zhaochen0110/OpenThinkIMG)" and "[Thinking with Images for Multimodal Reasoning](https://github.com/zhaochen0110/Awesome_Think_With_Images?tab=readme-ov-file)". Efficient reasoning is important for multimodality and may be especially important for **Thinking with images**. - [2025-06] Welcome to our latest paper "[Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning](https://arxiv.org/pdf/2506.04207)". We propose an Efficient-Length Reward for training multimodal reasoning models. - [2025-06] We include [MEM1](https://www.arxiv.org/pdf/2506.15841), where efficient reasoning is important for building Long-Horizon Agents. - [2025-05] We include LIMOPro for Efficient and Effective Reasoning in Test-time Scaling. - [2025-05] We update more papers on **adaptive reasoning**, which describe how a system/model autonomously switches between long and short reasoning chains based on problem complexity. - [2025-05] Welcome to our latest paper "[Scaling Reasoning, Losing Control](https://arxiv.org/pdf/2505.14810)", which shows that the longer the reasoning chain, the poorer its instruction-following ability. Therefore, efficient reasoning may also be important for **instruction following** in LRMs. - [2025-04] We include AgentPrune, where efficient reasoning is important for agent systems. - [2025-04] We include benchmarks for Efficient Reasoning: MME-CoT, S1-Bench, DUMB500. - [2025-04] We add Mamba Reasoning models (e.g M1) and Hybrid models (e.g Mamba-Transformer) in Efficient Reasoning during Pre-training. It is naturally efficient to infer. - [2025-04] We add a new "Model
Excerpt of 32,558 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c3adb7a6d9e6dd9d, llm:Repository description and topics: 'A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, Agent, and Beyond' with topics including chain-of-thought, efficient, efficient-reasoning, long-cot, reasoning, reasoning-budget, efficient-agents, overthinking, underthinking.
matched fp:c3adb7a6d9e6dd9d, llm:Repository description and topics: 'A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, Agent, and Beyond' with topics including chain-of-thought, efficient, efficient-reasoning, long-cot, reasoning, reasoning-budget, efficient-agents, overthinking, underthinking.
matched fp:c3adb7a6d9e6dd9d, llm:Repository description and topics: 'A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, Agent, and Beyond' with topics including chain-of-thought, efficient, efficient-reasoning, long-cot, reasoning, reasoning-budget, efficient-agents, overthinking, underthinking.