Agents Thinking Fast and Slow: A Talker-Reasoner Architecture
Keywords: thinking fast and slow, system 1 and system 2, language-based agents
TL;DR: We provide a new Talker-Reasoner language-based agent architecture, inspired by the two systems driving the way our minds work--- the fast and intuitive thinking System 1, and the slow and controlled multi-step reasoning/ planning System 2.
Abstract: Large language models have enabled agents of all kinds to interact with users through natural conversation. Consequently, agents now have two jobs: conversing and planning/reasoning. Their conversational responses must be informed by all available information, and their actions must help to achieve goals. This dichotomy between conversing with the user and doing multi-step reasoning and planning can be seen as analogous to the human systems of “thinking fast and slow” as introduced by Kahneman. Our approach is comprised of a "Talker" agent (System 1) that is fast and intuitive, and tasked with synthesizing the conversational response; and a "Reasoner" agent (System 2) that is slower, more deliberative, and more logical, and is tasked with multi-step reasoning and planning, calling tools, performing actions in the world, and thereby producing the new agent state. We describe the new Talker-Reasoner architecture and discuss its advantages, including modularity and decreased latency. We ground the discussion in the context of a sleep coaching agent, in order to demonstrate real-world relevance.
Submission Number: 23
Loading