LDM2: A Large Decision Model Imitating Human Cognition with Dynamic Memory Enhancement

Xingjin Wang, Linjing Li, Daniel Zeng


Abstract
With the rapid development of large language models (LLMs), it is highly demanded that LLMs can be adopted to make decisions to enable the artificial general intelligence. Most approaches leverage manually crafted examples to prompt the LLMs to imitate the decision process of human. However, designing optimal prompts is difficult and the patterned prompts can hardly be generalized to more complex environments. In this paper, we propose a novel model named Large Decision Model with Memory (LDM2), which leverages a dynamic memory mechanism to construct dynamic prompts, guiding the LLMs in making proper decisions according to the faced state. LDM2 consists of two stages: memory formation and memory refinement. In the former stage, human behaviors are decomposed into state-action tuples utilizing the powerful summarizing ability of LLMs. Then, these tuples are stored in the memory, whose indices are generated by the LLMs, to facilitate the retrieval of the most relevant subset of memorized tuples based on the current state. In the latter stage, our LDM2 employs tree exploration to discover more suitable decision processes and enrich the memory by adding valuable state-action tuples. The dynamic circle of exploration and memory enhancement provides LDM2 a better understanding of the global environment. Extensive experiments conducted in two interactive environments have shown that our LDM2 outperforms the baselines in terms of both score and success rate, which demonstrates its effectiveness.
Anthology ID:
2023.findings-emnlp.309
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4660–4681
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.309
DOI:
10.18653/v1/2023.findings-emnlp.309
Bibkey:
Cite (ACL):
Xingjin Wang, Linjing Li, and Daniel Zeng. 2023. LDM2: A Large Decision Model Imitating Human Cognition with Dynamic Memory Enhancement. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 4660–4681, Singapore. Association for Computational Linguistics.
Cite (Informal):
LDM2: A Large Decision Model Imitating Human Cognition with Dynamic Memory Enhancement (Wang et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.309.pdf