Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration
This addresses a critical bottleneck in human-AI interaction for applications requiring real-time collaboration, though it appears incremental as it builds on existing System 1/System 2 methods.
The paper tackles the problem of real-time simultaneous human-AI collaboration, where current LLM-based agents struggle with latency and inferring human strategies, by proposing DPT-Agent, a framework integrating System 1 (fast decision-making) and System 2 (reasoning-based decisions) based on Dual Process Theory, showing significant improvements over mainstream frameworks in experiments.
Agents built on large language models (LLMs) have excelled in turn-by-turn human-AI collaboration but struggle with simultaneous tasks requiring real-time interaction. Latency issues and the challenge of inferring variable human strategies hinder their ability to make autonomous decisions without explicit instructions. Through experiments with current independent System 1 and System 2 methods, we validate the necessity of using Dual Process Theory (DPT) in real-time tasks. We propose DPT-Agent, a novel language agent framework that integrates System 1 and System 2 for efficient real-time simultaneous human-AI collaboration. DPT-Agent's System 1 uses a Finite-state Machine (FSM) and code-as-policy for fast, intuitive, and controllable decision-making. DPT-Agent's System 2 integrates Theory of Mind (ToM) and asynchronous reflection to infer human intentions and perform reasoning-based autonomous decisions. We demonstrate the effectiveness of DPT-Agent through further experiments with rule-based agents and human collaborators, showing significant improvements over mainstream LLM-based frameworks. DPT-Agent can effectively help LLMs convert correct slow thinking and reasoning into executable actions, thereby improving performance. To the best of our knowledge, DPT-Agent is the first language agent framework that achieves successful real-time simultaneous human-AI collaboration autonomously. Code of DPT-Agent can be found in https://github.com/sjtu-marl/DPT-Agent.