Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912399838150656 |
|---|---|
| author | Zhang, Shao Wang, Xihuai Zhang, Wenhao Li, Chaoran Song, Junru Li, Tingyu Qiu, Lin Cao, Xuezhi Cai, Xunliang Yao, Wen Zhang, Weinan Wang, Xinbing Wen, Ying |
| author_facet | Zhang, Shao Wang, Xihuai Zhang, Wenhao Li, Chaoran Song, Junru Li, Tingyu Qiu, Lin Cao, Xuezhi Cai, Xunliang Yao, Wen Zhang, Weinan Wang, Xinbing Wen, Ying |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_11882 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration Zhang, Shao Wang, Xihuai Zhang, Wenhao Li, Chaoran Song, Junru Li, Tingyu Qiu, Lin Cao, Xuezhi Cai, Xunliang Yao, Wen Zhang, Weinan Wang, Xinbing Wen, Ying Artificial Intelligence Computation and Language Human-Computer Interaction Machine Learning Multiagent Systems 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. |
| title | Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration |
| topic | Artificial Intelligence Computation and Language Human-Computer Interaction Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2502.11882 |