SwiftSage:高速思考と低速思考を備えた生成的エージェントによる複雑な対話型タスクの解決
SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
人間の二重過程理論に着想を得て、小さな言語モデルによる直感的な行動生成とGPT-4による熟考的なサブゴール計画を組み合わせ、複雑な対話型推論タスクの性能を向上させたエージェントフレームワーク。
著者: Bill Yuchen Lin, Yicheng Fu, Karina Yang, Faeze Brahman, Shiyu Huang, Chandra Bhagavatula, Prithviraj Ammanabrolu, Yejin Choi, Xiang Ren
分類: cs.CL, cs.AI, cs.LG, cs.MA, cs.RO
原文アブストラクト
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 interactive tasks.
