Awesome-Efficient-Reasoning
Paper list for Efficient Reasoning.
https://github.com/hemingkx/Awesome-Efficient-Reasoning
Last synced: 5 days ago
JSON representation
-
Papers
-
Long-to-Short Chain-of-Thought
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - -findings-orange) 
- [pdf - orange)  
- [pdf - orange)  
- [pdf - to-Short-via-Model-Merging)], 2025.03.  
- [pdf - orange)  
- [pdf - orange) 
- [pdf - AI4Edu/LS-Mixture)], 2025.05.  
- [pdf - orange) 
- [pdf - orange)
- [pdf - Group/SEAL)], 2025.05.   
- [pdf - orange) 
- [pdf - -findings-orange) 
- [pdf - orange) 
- [pdf - -findings-orange) 
- [pdf - orange) 
- [pdf - orange)
- [pdf - orange)
- [pdf - orange)
- [pdf - Embodied-AGI/BudgetGuidance)], 2025.06. 
- [pdf - R1)], 2025.06. 
- [pdf - orange) 
- [pdf - orange)
- [pdf - NLP-Chang/ThinkPrune)], 2025.04.  
- [pdf - orange)
- [pdf - orange)
- [pdf - orange)  
- [pdf - orange)  
- [pdf - orange) 
- [pdf - orange)  
- [pdf - orange) 
- [pdf - orange)
- [pdf - orange)
- [pdf - orange) 
- [pdf - nlp-lab/LengthReward)], 2025.06. 
- [pdf - Policy-Preference-Optimization)], 2025.07. 
- [pdf - orange) 
- [pdf - orange)
- [pdf - orange) 
- [pdf - -findings-orange)
- [pdf - orange) 
- [pdf - orange)  
- [pdf - otimes-Short/)], 2025.05. 
- [pdf - orange)
- [pdf - orange)
- [pdf - orange) 
- [pdf - orange)  
- [pdf - orange)  
- [pdf - sg/AnytimeReasoner)], 2025.05.   
- [pdf - orange)  
- [pdf - nlp/Laser)], 2025.05.  
- [pdf - orange) 
- [pdf - orange)
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange)  
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - Reasoning-Efficiency)], 2025.06.  
- [pdf - paper/)], [[code](https://github.com/royeisen/reasoning_loading_bar)], 2025.06. 
- [pdf - Thought)], 2025.05.  
- [pdf - orange)  
- [pdf - of-symbol-planning)], 2023.05. 
- [pdf - orange) 
- [pdf - Pruner)], 2025.01.  
- [pdf - orange) 
- [pdf - Labs/efficient-reasoning)], [[homepage](https://zanette-labs.github.io/efficient-reasoning/)], 2025.02. 
- [pdf - orange) 
- [pdf - -findings-orange)  
- [pdf - concise-cot)], 2024.01.  
- [pdf - orange) 
- [pdf - of-draft)], 2025.02.   
- [pdf - CoT/compressed-cot)], 2025.03.  
- [pdf - orange)  
- [pdf - Valve)], 2025.02.  
- [pdf - reasoning)], 2025.02. 
- [pdf - l3/l1)], [[homepage](https://cmu-l3.github.io/l1/)], 2025.03.   
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange)
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange)
- [pdf - orange) 
- [pdf - real/hbpo)], 2025.09.  
- [pdf - orange) 
- [pdf - orange)
- [pdf - orange) 
- [pdf - dev/ReasoningPathCompression)], 2025.05.  
- [pdf - orange) 
- [pdf - Enough-Think)], 2025.09.  
- [pdf - orange) 
- [pdf - KEG/siri)], 2025.10.  
-
Analysis
- [pdf - orange)
- [pdf - orange) 
- [pdf - orange) 
- [pdf - lab/MiP-Overthinking)], 2025.04.  
- [pdf - orange) 
- [pdf - orange) 
- [pdf - ov-file)], 2025.06. 
- [pdf - latent-cot)], 2025.07. 
- [pdf - orange) 
- [pdf - USTC/LRM-plans-CoT)], 2025.06.  
- [pdf - orange) 
- [pdf - Impact-of-Reasoning-Step-Length-on-Large-Language-Models)], 2024.01.  
- [pdf - boundary)], 2024.10.  
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange)
- [pdf - 32B)], 2025.03. 
- [pdf - orange) 
- [pdf - try-matters)], 2025.10. 
- [pdf - orange)
-
Small Reasoning Models & CoT Distillation
- [pdf - NLP/Distilling-CoT-Reasoning)], 2025.02. 
- [pdf - orange)
- [pdf - orange)
- [pdf - -findings-orange)
- [pdf - z/SCORE)], 2024.04. 
- [pdf - orange) 
- [pdf - orange)
- [pdf - optimal-tts)], [[homepage](https://ryanliu112.github.io/compute-optimal-tts/)], 2025.02.  
- [pdf - orange)
- [pdf - orange)
- [pdf - orange) 
- [pdf - -short-orange)
- [pdf - wang/Tina)], 2025.04.  
- [pdf - orange)
- [pdf - luo/SODE)], 2025.03.  
- [pdf - nlp/simpleRL-reason)], 2025.03.   
- [pdf - rs)], 2025.03. 
- [pdf - orange) 
- [pdf - Model-Gap/Small-Model-Learnability-Gap)], [[homepage](https://small-model-gap.github.io/)], 2025.02. 
- [pdf - USTC/TFPI-temp)], 2025.09. 
-
Speculative Decoding for CoT Efficiency
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - ai-lab/LookaheadReasoning)], 2025.06. 
- [pdf - orange) 
- [pdf - RL)], 2025.09.  
- [pdf - orange) 
-
Survey
- [pdf - Efficient-R1-style-LRMs)], 2025.07. 
- [pdf - Efficient-Reasoning-Models)], 2025.04. 
- [pdf - llm-implicit-reasoning)], 2025.09. 
- [pdf - orange)
- [pdf - art-projection/LatentCoT-Horizon/)], 2025.07. 
- [pdf - orange)
- [pdf - Efficient-Reasoning-LLMs)], 2025.03. 
- [pdf - orange)
- [pdf - Efficient-Inference-for-LRMs)], 2025.03. 
- [pdf - Reasoning-Economy-Papers)], 2025.03. 
-
Other Work
- [pdf - orange)  
- [pdf - orange)
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange)  
- [pdf - orange)  
- [pdf - orange)
- [pdf - orange)
- [pdf - orange)
-
Efficient Training
- [pdf - orange) 
- [pdf - orange) 
- [pdf - lime/verl)], 2025.04.  
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - R1)], 2025.03.  
- [pdf - ai-lab.github.io/GRESO/)], [[code](https://github.com/Infini-AI-Lab/GRESO)], 2025.06.  
- [pdf - cpu/Question-Free-Fine-Tuning)], 2025.06.  
- [pdf - PO)], 2025.05.  
- [pdf - wang.github.io/high-entropy-minority-tokens-rlvr/)], 2025.06.  
- [pdf - Group/EPiC)], 2025.06.   
- [pdf - orange) 
- [pdf - sg/understand-r1-zero)], 2025.03.  
- [pdf - R1)], 2025.03.  
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - NLP/LIMO)], 2025.02.  
- [pdf - orange) 
- [pdf - orange) 
- [pdf - SIA/DAPO)], [[homepage](https://dapo-sia.github.io/)], 2025.03.  
- [pdf - orange) 
- [pdf - ustc/Alpha-RL)], 2025.10.  
-
Latent Chain-of-Thought
- [pdf - orange)
- [pdf - orange)
- [pdf - orange) 
- [pdf - ai-lab/Soft-Thinking)], 2025.05.  
- [pdf - NLP/Awesome-Latent-CoT)], 2025.05.  
- [pdf - latent-reasoning.github.io/)], 2025.05.  
- [pdf - orange)
- [pdf - orange) 
- [pdf - orange)
- [pdf - orange)
- [pdf - orange)
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange)
- [pdf - orange) 
- [pdf - Memory-and-Reasoning)], 2024.11. 
- [pdf - orange) 
- [pdf - orange)  
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange)
- [pdf - orange) 
- [pdf - rg/recurrent-pretraining)], 2025.02. 
- [pdf - orange)  
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange)
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange)
- [pdf - orange)  
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange)
- [pdf - CoT)], 2025.09.  
-
Small & Large Reasoning Model Collaboration
- [pdf - orange)
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange)
- [pdf - orange) 
- [pdf - orange)  
- [pdf - orange)  
- [pdf - orange)  
-
Optimal Test-Time Scaling
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange)
- [pdf - orange) 
- [pdf - gh98/Guided-by-Gut)], 2025.05. 
- [pdf - guided-search)], 2025.05. 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - First-Search)], 2025.06.  
- [pdf - orange)
- [pdf - orange)
- [pdf - wyz/inference_scaling)], [[homepage](https://thu-wyz.github.io/inference-scaling/)], 2024.08. 
- [pdf - orange)
- [pdf - orange) 
- [pdf - time-scaling-eval)], 2025.02.  
- [pdf - orange) 
- [pdf - orange) 
- [pdf - genrm-scaling)], 2025.04. 
- [pdf - orange) 
- [pdf - AIRe/MRT)], [[homepage](https://cohenqu.github.io/mrt.github.io/)], 2025.03.  
- [pdf - orange) 
- [pdf - orange)
- [pdf - orange) 
-
Parallel Thinking
- [pdf - AI-Lab/Multiverse)], 2025.05. 
- [pdf - orange)
- [pdf - orange)  
- [pdf - Reasoning/APR)], 2025.04.   
- [pdf - orange)
- [pdf - decoding-in-one-sequence)], 2024.03.  
- [pdf - research/sot)], [[homepage](https://sites.google.com/view/sot-llm)], 2023.06.  
- [pdf - orange)
- [pdf - orange)
-
Reasoning Shortcuts
- [pdf - orange)  
- [pdf - orange)
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange)  
- [pdf - yibo/R1-Compress)], 2025.05.   
- [pdf - All-Thinking-Tokens)], 2025.05.  
- [pdf - NLP/LIMOPro)], 2025.05.   
- [pdf - orange)  
- [pdf - orange) 
-
Benchmarks
- [pdf - orange) 
- [pdf - orange) 
- [pdf - bench.github.io/)], [[code](https://github.com/ZhiyuanLi218/Think-Bench)], 2025.04.  
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
-
Multimodal Reasoning Efficiency
- [pdf - 4B)], [[huggingface](https://huggingface.co/YannQi/R-4B)], 2025.08.  
- [pdf - zju/PixelThink)], [[homepage](https://pixelthink.github.io/)], 2025.05.  
- [pdf - orange)
- [pdf - fuxi.github.io/projects/uni-cot/)], 2025.09.  
-
Adaptive Thinking
- [pdf - orange) 
- [pdf - orange)
- [pdf - KEG/AdaptThink)], 2025.05.  
- [pdf - orange) 
- [pdf - orange)
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - project.github.io/)], [[code](https://github.com/ASTRAL-Group/AlphaOne)], 2025.05.  
- [pdf - Lab/OThink-R1)], 2025.05.  
- [pdf - orange) 
- [pdf - fib-lab/Token_Signature)], 2025.06. 
- [pdf - orange) 
- [pdf - orange)
- [pdf - orange)
- [pdf - arm.github.io/arm/)], [[code](https://github.com/TEAM-ARM/ARM)], 2025.05.  
-
Sparse Attention & KV Cache
-
Efficient Sampling
- [pdf - orange)
- [pdf - orange)
- [pdf - orange)
- [pdf - Labs/SpeculativeRejection)], 2024.10.   
- [pdf - github-00/LLM-Predictive-Decoding)], 2024.10.  
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - orange)  
- [pdf - orange) 
- [pdf - Decoding)], 2025.03.  
-
Reasoning Step Decomposition
- [pdf - yw/Markov-Chain-of-Thought)], 2024.10.   
- [pdf - orange) 
- [pdf - -FM_workshop-orange) 
- [pdf - orange)  
- [pdf - orange) 
-
Efficient Self-Consistency
- [pdf - orange) 
- [pdf - -Findings-orange) 
- [pdf - orange) 
- [pdf - orange) 
- [pdf - Huang/Self-Calibration)], 2025.02.  
- [pdf - orange) 
- [pdf - -findings-orange) 
- [pdf - orange) 
-
Long-Context Reasoning Efficiency
-
Applications
-
-
Resources
-
Applications
- yuelinan/Awesome-Efficient-R1-style-LRMs
- Eclipsess/Awesome-Efficient-Reasoning-LLMs
- XiaoYee/Awesome_Efficient_LRM_Reasoning
- Blueyee/Efficient-CoT-LRMs
- yueliu1999/Awesome-Efficient-Inference-for-LRMs
- DevoAllen/Awesome-Reasoning-Economy-Papers
- Hongcheng-Gao/Awesome-Long2short-on-LRMs
- EIT-NLP/Awesome-Latent-CoT
- yzhangchuck/awesome-llm-reasoning-long2short-papers
- fscdc/Awesome-Efficient-Reasoning-Models
-
-
Keywords Convention
-
Blog & Project
-
Talks
-
Applications
-
Sub Categories
Long-to-Short Chain-of-Thought
100
Latent Chain-of-Thought
36
Efficient Training
24
Optimal Test-Time Scaling
23
Analysis
22
Small Reasoning Models & CoT Distillation
20
Adaptive Thinking
18
Applications
16
Reasoning Shortcuts
12
Efficient Sampling
11
Survey
10
Speculative Decoding for CoT Efficiency
10
Other Work
9
Parallel Thinking
9
Small & Large Reasoning Model Collaboration
8
Efficient Self-Consistency
8
Benchmarks
6
Reasoning Step Decomposition
5
Sparse Attention & KV Cache
4
Multimodal Reasoning Efficiency
4
Long-Context Reasoning Efficiency
2