ReAct

Yao et al., 2022 (opens in a new tab) introduced a framework where LLMs are used to generate both reasoning traces and task-specific actions in an interleaved manner. Generating reasoning traces allow the model to induce, track, and update action plans, and even handle exceptions. The action step allows to interface with and gather information from external sources such as knowledge bases or environments.

Yao等人，2022 (opens in a new tab) 提出了一個框架，其中LLMs以交替的方式產生推理追蹤和任務特定的操作。產生推理追蹤使模型能夠誘導、追蹤和更新行動計劃，甚至處理異常情況。行動步驟允許與外部來源（如知識庫或環境）進行介面和收集資訊。

The ReAct framework can allow LLMs to interact with external tools to retrieve additional information that leads to more reliable and factual responses.

ReAct框架可以讓LLMs與外部工具互動，以檢索更多的資訊，從而得出更可靠和事實的回答。

Image Source: Yao et al., 2022 (opens in a new tab)

圖片來源：Yao et al.，2022 (opens in a new tab)

Full example coming soon!

Full example coming soon!