deepseek-ai/DeepSeek-R1
Text Generation
•
685B
•
Updated
•
568k
•
•
13k
LLM Reasoning & Planning Techniques
CoT, ToT, GoT, ReAct, ReWOO prompting techniques for LLM reasoning with implementation guidance and benchmarks.
Note Pure reasoning model
Qwen/Qwen2.5-Coder-32B-Instruct
Text Generation • 33B • Updated • 725k • • 1.99kNote Code reasoning specialist
google/gemma-2-27b-it
Text Generation • 27B • Updated • 392k • 559Note Strong CoT performance
-
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Paper • 2201.11903 • Published • 15 -
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Paper • 2305.10601 • Published • 15 -
Graph of Thoughts: Solving Elaborate Problems with Large Language Models
Paper • 2308.09687 • Published • 7 -
Least-to-Most Prompting Enables Complex Reasoning in Large Language Models
Paper • 2205.10625 • Published • 1 -
ReAct: Synergizing Reasoning and Acting in Language Models
Paper • 2210.03629 • Published • 32 -
ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
Paper • 2305.18323 • Published • 1 -
Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding
Paper • 2307.15337 • Published • 39 -
Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models
Paper • 2310.06117 • Published • 2 -
Language Models are Few-Shot Learners
Paper • 2005.14165 • Published • 19 -
Large Language Models Understand and Can be Enhanced by Emotional Stimuli
Paper • 2307.11760 • Published • 1 -
DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
Paper • 2310.03714 • Published • 37