SwiftSage：一個具有快速和慢速思考能力的生成式代理程式，適用於複雜的互動任務。

摘要

我們介紹了 SwiftSage，這是一個新穎的代理人框架，靈感來自於人類認知的雙系統理論，旨在在複雜互動推理任務中擅長行動規劃。SwiftSage 將行為克隆和提示大型語言模型（LLMs）的優勢相結合，以提高任務完成性能。該框架包括兩個主要模塊：Swift 模塊代表快速直覺思考，而 Sage 模塊則模擬深思熟慮的思維過程。Swift 模塊是在神諭代理人的行動軌跡上進行微調的小型編碼器-解碼器 LM，而 Sage 模塊則使用像 GPT-4 這樣的LLMs進行子目標規劃和基礎建立。我們開發了一種啟發式方法，將這兩個模塊和諧地整合在一起，從而實現更高效和更穩健的問題解決過程。在來自 ScienceWorld 基準的 30 個任務中，SwiftSage明顯優於其他方法，如 SayCan、ReAct 和 Reflexion，展示了其在解決複雜現實任務中的有效性。

English

We introduce SwiftSage, a novel agent framework inspired by the dual-process theory of human cognition, designed to excel in action planning for complex interactive reasoning tasks. SwiftSage integrates the strengths of behavior cloning and prompting large language models (LLMs) to enhance task completion performance. The framework comprises two primary modules: the Swift module, representing fast and intuitive thinking, and the Sage module, emulating deliberate thought processes. The Swift module is a small encoder-decoder LM fine-tuned on the oracle agent's action trajectories, while the Sage module employs LLMs such as GPT-4 for subgoal planning and grounding. We develop a heuristic method to harmoniously integrate the two modules, resulting in a more efficient and robust problem-solving process. In 30 tasks from the ScienceWorld benchmark, SwiftSage significantly outperforms other methods such as SayCan, ReAct, and Reflexion, demonstrating its effectiveness in solving complex real-world tasks.

SwiftSage：一個具有快速和慢速思考能力的生成式代理程式，適用於複雜的互動任務。

SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks

摘要

Support