ReAct (prompting)
ReAct (short for Reasoning and Acting) is a prompting paradigm for large language models that interleaves verbal reasoning traces ("Thoughts") with task-specific actions executed against an external…
Prompt Engineering
Explore Prompt Engineering through related topics and the articles other pages reference most.
Explore articles
Browse subtopics: Reasoning Models
Articles that also belong to these categories. Counts cover all of Prompt Engineering.
All articles (27)Large Language Models (13)Natural Language Processing (5)Artificial Intelligence (4)Machine Learning (4)AI Agents (3)Reasoning Models (3)ChatGPT (2)AI Code Generation (1)AI Inference (1)AI Safety (1)AI Tools & Products (1)Deep Learning (1)Image Generation (1)OpenAI (1)Software Development (1)
Showing 1-3 of 3 articles
Self-consistency
Self-consistency is a decoding strategy for large language models that samples multiple chain-of-thought reasoning paths for the same question and returns the answer that the majority of those paths agree on
Tree of Thoughts
Tree of Thoughts (ToT) is a prompting and inference-time search framework for large language models that lets the model explore multiple intermediate reasoning steps as nodes in a tree, evaluate each…