Announcing our new Course: AI Red-Teaming and AI Safety Masterclass

Check it out →

≡

Learn Prompting

Prompt Engineering Guide

😃 Basics

🟢 Introduction to AI

🟢 Prompting With ChatGPT

🟢 Prompt Engineering

🟢 Learn Prompting Embeds

🟢 Giving Instructions

🟢 Assigning Roles

🟢 Few-Shot Prompting

🟢 Parts of a Prompt

🟢 Combining Techniques

🟢 Priming Chatbots

🟢 OpenAI Playground

🟢 LLM Settings

🟢 Pitfalls of LLMs

🟢 Understanding AI Minds

🟢 The Learn Prompting Method

🟢 Starting Your Journey

💼 Applications

🟢 Introduction

🟢 Summarizing Text

🟢 Structuring Data

🟢 Writing An Email

🟢 Different Writing Styles

🟢 Zapier for Emails

🟢 Study Buddy

🟦 Coding Assistance

🟦 Digital Marketing

🟢 Finding Emojis

🟢 Multiple Choice Questions

🟢 Solve Discussion Questions

🟢 How to Build a Chatbot Using LLMs

🟢 Chatbot + Knowledge Base

🧙‍♂️ Intermediate

🟢 Introduction

🟢 Chain-of-Thought Prompting

🟢 Zero-Shot Chain-of-Thought

🟦 Self-Consistency

🟦 Generated Knowledge

🟦 Least-to-Most Prompting

🟦 Dealing With Long Form Content

🟦 Revisiting Roles

🟢 What's in a Prompt?

🧠 Advanced

🟢 Introduction

Zero-Shot

🟢 Introduction

🟢 Emotion Prompting

🟢 Role Prompting

🟢 Re-reading (RE2)

🟢 Rephrase and Respond (RaR)

◆ System 2 Attention (S2A)

Few-Shot

🟢 Introduction

◆ K-Nearest Neighbor (KNN)

◆◆ Prompt Mining

Thought Generation

🟢 Introduction

🟦 Contrastive Chain-of-Thought

🟦 Automatic Chain of Thought (Auto-CoT)

🟦 Tabular Chain of Thought (Tab-CoT)

🟦 Memory-of-Thought (MoT)

🟦 Active Prompting

🟦 Analogical Prompting

🟦 Complexity-Based Prompting

🟦 Step-Back Prompting

Ensembling

🟢 Introduction

🟦 Mixture of Reasoning Experts (MoRE)

🟦 Consistency-based Self-adaptive Prompting (COSP)

🟦 DiVeRSe (Diverse Verifier on Reasoning Step)

Self-Criticism

🟢 Introduction

🟢 Self-Calibration

🟢 Chain-of-Verification (CoVe)

🟦 Self-Refine

🟦 Cumulative Reasoning

🟦 Reversing Chain-of-Thought (RCoT)

◆ Self-Verification

Decomposition

🟢 Introduction

🟦 Decomposed Prompting

🟦 Plan-and-Solve Prompting

🟦 Program of Thoughts

🟦 Tree of Thoughts

◆ Faithful Chain-of-Thought

◆ Recursion of Thought

◆ Skeleton-of-Thought

🌱 New Techniques

🟢 Introduction

🟦 Self-Harmonized Chain of Thought (ECHO)

🟦 Logic-of-Thought (LoT)

🟦 Code Prompting

◆ End-to-End DAG-Path (EEDP) Prompting

◆ Instance-adaptive Zero-shot Chain-of-Thought Prompting (IAP)

👀 For Vision-Language Models (VLMs)

🟢 Prompt Learning

◆ Context Optimization (CoOp)

◆ Conditional Prompt Learning (CoCoOp)

◆ Mixture of Prompt Learning (MoCoOp)

◆ Attention Prompting on Image

🔀 For Multimodal Large Language Models (MLLMs)

◆ Visual Prompting

🤖 Agents

🟢 Introduction

🟦 LLMs Using Tools

🟦 LLMs that Reason and Act

🟦 Code as Reasoning

⚖️ Reliability

🟢 Introduction

🟢 Prompt Debiasing

🟦 Prompt Ensembling

🟦 LLM Self-Evaluation

🟦 Calibrating LLMs

🖼️ Image Prompting

🟢 Introduction

🟢 Style Modifiers

🟢 Quality Boosters

🟢 Repetition

🟢 Weighted Terms

🟢 Fix Deformed Generations

🟢 Midjourney

🔓 Prompt Hacking

🔨 Tooling

💪 Prompt Tuning

🟢 Introduction

Interpretable Soft Prompts

🗂️ RAG

🟢 Introduction

🟦 Multi-Fusion Retrieval Augmented Generation (MoRAG)

🎲 Miscellaneous

🟢 Detecting AI Generated Text

🟢 Introduction

🟢 Detection Trickery

🟢 Music Generation

📝 Language Models

🟢 Introduction

📙 Vocabulary Reference

📚 Bibliography

📦 Prompted Products

🛸 Additional Resources

🔥 Hot Topics

🤖 Agents🟦 LLMs that Reason and Act

🟦 LLMs that Reason and Act

Last updated on August 7, 2024 by Sander Schulhoff

What is ReAct?

ReAct (Reason + Act)¹ is a paradigm that enables Large Language Models (LLMs) to solve complex tasks through natural language reasoning and actions. It allows an LLM to perform certain actions, such as retrieving external information, and then reason based on the retrieved data.

ReAct systems extend Modular Reasoning, Knowledge, and Language (MRKL) systems by adding the ability to reason about the actions they can perform.

Example

Below is an example from HotPotQA², a question-answering dataset requiring complex reasoning. ReAct allows the LLM to reason about the question (Thought 1), take actions (e.g., querying Google) (Act 1). It then receives an observation (Obs 1) and continues the thought-action loop until reaching a conclusion (Act 3).

ReAct System (Yao et al.)

Readers with knowledge of Reinforcement Learning (RL) may recognize this process as similar to the classic RL loop of state, action and reward. ReAct provides some formalization for this in their paper.

Results

Google experimented with the PaLM LLM³ using ReAct, and the results showed promising improvements in complex reasoning tasks. ReAct was tested on datasets such as FEVER⁴, focusing on fact extraction and verification.

ReAct Results (Yao et al.)

Footnotes

Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., & Cao, Y. (2022). ↩
Yang, Z., Qi, P., Zhang, S., Bengio, Y., Cohen, W. W., Salakhutdinov, R., & Manning, C. D. (2018). HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering. ↩
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H. W., Sutton, C., Gehrmann, S., Schuh, P., Shi, K., Tsvyashchenko, S., Maynez, J., Rao, A., Barnes, P., Tay, Y., Shazeer, N., Prabhakaran, V., … Fiedel, N. (2022). PaLM: Scaling Language Modeling with Pathways. ↩
Thorne, J., Vlachos, A., Christodoulopoulos, C., & Mittal, A. (2018). FEVER: a large-scale dataset for Fact Extraction and VERification. ↩

Word count: 0

Previous

🟦 LLMs Using Tools

🟦 Code as Reasoning

Next

Get AI Certified by Learn Prompting

Need Business GenAI Training?

Contact Sales

Want to keep learning

Course Catalog

Want to test your knowledge

Certification Exam

Questions?

Contact Sales

Copyright © 2024 Learn Prompting.