| created | modified | tags | type | status | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
|
2024-07-15 13:30 |
|
|
|
(paper) ReAct: Synergizing Reasoning and Acting in Language Models (https://arxiv.org/abs/2210.03629)
ReAct prompting is a prompting style used to induce reasoning from LLMs in an [[LLM Agents]] system.
ReAct prompting involves inducing the large language model to solve a problem through multiple thought-action-observation steps. This is achieved through few-shot prompting i.e. including several examples of how it the task should be solved within the prompt, before giving the model the actual task.
Here is an example prompt from the original paper: (this is just showing the model a single example - the real prompt should contain multiple examples): QUESTION: Were Pavel Urysohn and Leonid Levin known for the same type of work? THOUGHT 1: I need to search Pavel Urysohn and Leonid Levin, find their types of work, then find if they are the same. ACTION 1: Search[Pavel Urysohn] OBSERVATION 1: Pavel Samuilovich Urysohn (February 3, 1898 - August 17, 1924) was a Soviet mathematician who is best known for his contributions in dimension theory. THOUGHT 2: Pavel Urysohn is a mathematician. I need to search Leonid Levin next and find its type of work. Action 2: Search[Leonid Levin] Observation 2: Leonid Anatolievich Levin is a Soviet-American mathematician and computer scientist. Thought 3: Leonid Levin is a mathematician and computer scientist. So Pavel Urysohn and Leonid Levin have the same type of work. Action 3: Finish[yes]
- [[Applied Large Language Model Concepts]]
- ReAct: Synergizing Reasoning and Acting in Language Models https://arxiv.org/abs/2210.03629