LDM$^2$: A Large Decision Model Imitating Human Cognition with Dynamic Memory Enhancement

Xingjin Wang, Linjing Li, Daniel Dajun Zeng

Submission Type: Regular Long Paper

Submission Track: Theme Track: Large Language Models and the Future of NLP

Submission Track 2: NLP Applications

Keywords: Large Language Model, Decision Making, Memory Enhanced

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 (LDM$^2$), which leverages a dynamic memory mechanism to construct dynamic prompts, guiding the LLMs in making proper decisions according to the faced state.
LDM$^2$ 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 LDM$^2$ 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 LDM$^2$ a better understanding of the global environment.
Extensive experiments conducted in two interactive environments have shown that our LDM$^2$ outperforms the baselines in terms of both score and success rate, which demonstrates its effectiveness.

Submission Number: 3207