Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration

TL;DR

This paper introduces DPT-Agent, a novel language agent framework that leverages Dual Process Theory to enable real-time, simultaneous human-AI collaboration, overcoming latency and inference challenges of existing models.

Contribution

The paper presents DPT-Agent, the first framework integrating System 1 and System 2 processes for autonomous, real-time human-AI collaboration using language models.

Findings

DPT-Agent significantly outperforms existing LLM frameworks in real-time tasks.

DPT-Agent effectively infers human intentions and makes autonomous decisions.

The framework demonstrates successful collaboration with both rule-based agents and humans.

Abstract

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.