SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
This work addresses complex interactive reasoning tasks for AI agents, representing an incremental advancement by combining existing techniques in a novel framework.
The authors tackled the problem of action planning for complex interactive reasoning tasks by introducing SwiftSage, a generative agent framework that integrates behavior cloning and prompting large language models, resulting in significant performance improvements over other methods in 30 tasks from the ScienceWorld benchmark.
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.