Shadowgraph
TrendingAbout
Sign in

StarDewXXX/Awesome-Hybrid-CoT-Reasoning

63

18 commits

updated Jun 7, 2025

See the code

README

A curated list of research papers on Hybrid (Adaptive) Chain-of-Thought (CoT) Reasoning.

Awesome-Hybrid-CoT-Reasoning 🧠🤔

Hybrid Chain-of-Thought (CoT) is a novel technique designed to accelerate the reasoning process of large reasoning models. It aims to enable the model to dynamically select between Long-CoT and Short-CoT strategies based on the nature of the problem, achieving significantly greater speedup compared to alternative approaches.

📌 LLMs Paper List (sorted by time)

TitlePublished DateLink
Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization2025-04🔗 arXiv
Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL2025-05🔗 arXiv
Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning2025-05🔗 arXiv
AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning2025-05🔗 arXiv
Thinkless: LLM Learns When to Think2025-05🔗 arXiv
AdaptThink: Reasoning Models Can Learn When to Think2025-05🔗 arXiv
ThinkSwitcher: When to Think Hard, When to Think Fast2025-05🔗 arXiv
Think Only When You Need with Large Hybrid-Reasoning Models2025-05🔗 arXiv
Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning2025-05🔗 arXiv
AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting2025-05🔗 arXiv
Adaptive Deep Reasoning: Triggering Deep Thinking When Needed2025-05🔗 arXiv
Learn to Reason Efficiently with Adaptive Length-based Reward Shaping2025-05🔗 arXiv
ARM: Adaptive Reasoning Model2025-05🔗 arXiv

📌 MLLMs Paper List (sorted by time)

TitlePublished DateLink
Fast-Slow Thinking for Large Vision-Language Model Reasoning2025-04🔗 arXiv

📌 Open source LLMs (sorted by time)

TitlePublished DateLink
Qwen3 Series (Qwen Team)2025-04🔗 arXiv
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought2025-05🔗 arXiv

Contributors

StarDewXXX

11 commits

w-yibo

5 commits

wannanfeng

2 commits

Similar repos

fscdc/Awesome-Efficient-Reasoning-Models

[TMLR 2025] Efficient Reasoning Models: A Survey

321

XiaoYee/Awesome_Efficient_LRM_Reasoning

😎 A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, Agent, and…

360

yueliu1999/Awesome-Efficient-Inference-for-LRMs

[IEEE T-PAMI] Awesome-Efficient-Inference-for-LRMs is a collection of state-of-the-art, novel,…

242

Blueyee/Efficient-CoT-LRMs

Chain of Thoughts (CoT) is so hot! so long! We need short reasoning process!

72

atfortes/Awesome-LLM-Reasoning

From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓

3,686

DevoAllen/Awesome-Reasoning-Economy-Papers

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

124

Hongcheng-Gao/Awesome-Long2short-on-LRMs

Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods…

262

LightChen233/Awesome-Long-Chain-of-Thought-Reasoning

Latest Advances on Long Chain-of-Thought Reasoning

649

StarDewXXX/Awesome-Hybrid-CoT-Reasoning

63

18 commits

updated Jun 7, 2025

See the code

README

A curated list of research papers on Hybrid (Adaptive) Chain-of-Thought (CoT) Reasoning.

Awesome-Hybrid-CoT-Reasoning 🧠🤔

Hybrid Chain-of-Thought (CoT) is a novel technique designed to accelerate the reasoning process of large reasoning models. It aims to enable the model to dynamically select between Long-CoT and Short-CoT strategies based on the nature of the problem, achieving significantly greater speedup compared to alternative approaches.

📌 LLMs Paper List (sorted by time)

TitlePublished DateLink
Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization2025-04🔗 arXiv
Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL2025-05🔗 arXiv
Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning2025-05🔗 arXiv
AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning2025-05🔗 arXiv
Thinkless: LLM Learns When to Think2025-05🔗 arXiv
AdaptThink: Reasoning Models Can Learn When to Think2025-05🔗 arXiv
ThinkSwitcher: When to Think Hard, When to Think Fast2025-05🔗 arXiv
Think Only When You Need with Large Hybrid-Reasoning Models2025-05🔗 arXiv
Prolonged Reasoning Is Not All You Need: Certainty-Based Adaptive Routing for Efficient LLM/MLLM Reasoning2025-05🔗 arXiv
AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting2025-05🔗 arXiv
Adaptive Deep Reasoning: Triggering Deep Thinking When Needed2025-05🔗 arXiv
Learn to Reason Efficiently with Adaptive Length-based Reward Shaping2025-05🔗 arXiv
ARM: Adaptive Reasoning Model2025-05🔗 arXiv

📌 MLLMs Paper List (sorted by time)

TitlePublished DateLink
Fast-Slow Thinking for Large Vision-Language Model Reasoning2025-04🔗 arXiv

📌 Open source LLMs (sorted by time)

TitlePublished DateLink
Qwen3 Series (Qwen Team)2025-04🔗 arXiv
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought2025-05🔗 arXiv

Similar repos

fscdc/Awesome-Efficient-Reasoning-Models

[TMLR 2025] Efficient Reasoning Models: A Survey

321

XiaoYee/Awesome_Efficient_LRM_Reasoning

😎 A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, Agent, and…

360

yueliu1999/Awesome-Efficient-Inference-for-LRMs

[IEEE T-PAMI] Awesome-Efficient-Inference-for-LRMs is a collection of state-of-the-art, novel,…

242

Blueyee/Efficient-CoT-LRMs

Chain of Thoughts (CoT) is so hot! so long! We need short reasoning process!

72

atfortes/Awesome-LLM-Reasoning

From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓

3,686

DevoAllen/Awesome-Reasoning-Economy-Papers

Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

124

Hongcheng-Gao/Awesome-Long2short-on-LRMs

Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods…

262

LightChen233/Awesome-Long-Chain-of-Thought-Reasoning

Latest Advances on Long Chain-of-Thought Reasoning

649

Contributors

StarDewXXX

11 commits

w-yibo

5 commits

wannanfeng

2 commits