把它留给大型语言模型! 用内存集成进行校正和规划
Yuan Zhang1,2, Chao Wang1,2, Juntong Qi1,2
1School of Future Technology, Shanghai University, Shanghai, China.
Cyborg and bionic systems (Washington, D.C.)
|March 29, 2024
概括
本研究介绍了CPMI,一种新的LLM中心方法,用于实现AI任务,如视觉语言导航. 通过使动态规划和执行成为可能,CPMI提高了代理商的性能,提高了在少数情况下的成功率和效率.
科学领域:
- 人工智能的人工智能
- 机器人技术 机器人技术 机器人技术
- 自然语言处理自然语言处理.
背景情况:
- 传统的视觉语言导航 (VLN) 依赖于昂贵的手动标签,用于新环境中的任务规划.
- 大型语言模型 (LLM) 提供了常识知识,但由于障碍和状态变化,在体现的任务中难以动态执行.
- 在VLN中单一平面的方法是脆弱的,容易因轻微的执行错误而失败.
研究的目的:
- 开发一种更有效,更具成本效益的方法,使代理人能够理解和执行体现任务中的自然语言指令.
- 为了利用LLM的推理能力,在任务执行过程中进行动态规划和适应.
- 为了提高代理商的性能和成功率,在VLN的短暂学习场景中进行VLN.
主要方法:
- 提出了一种名为 Correction and Planning with Memory Integration (CPMI) 的新方法,以大型语言模型 (LLM) 为中心.
- 在LLM中心的规划器中集成了辅助模块,以提供记忆和通用体验机制.
- 基于环境反,在任务执行期间促进了动态规划和实时调整.
主要成果:
- 在公开数据集上,CPMI在一些射击学习场景中表现出卓越的表现.
- 这种方法显著提高了任务完成的效率.
- 执行自然语言指令的代理人的成功率大幅增加.
结论:
- 通过使动态规划和适应,CPMI方法有效地提高了LLM对体现任务的能力.
- 记忆和通用体验机制对于提高执行期间的代理性能至关重要.
- 对于更强大,更有效的体内人工智能代理来说,CPMI提供了一个有希望的方向,特别是在低数据制度中.
更多相关视频
相关概念视频
Language and Cognition
343
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
343
Elaborative Rehearsals
86
Elaborative rehearsal is a crucial cognitive strategy that strengthens information encoding in long-term memory by making meaningful connections between new data and pre-existing knowledge. This approach contrasts with maintenance rehearsal, which involves simple repetition without delving into the significance of the information. While maintenance rehearsal might temporarily keep information active in short-term memory, it is less effective for long-term retention.
The effectiveness of...
The effectiveness of...
86
Storage
84
A schema is a mental framework that helps individuals organize and interpret information. Schemata, formed from previous experiences, influence how we process new information: how we encode it, the inferences we make, and how we retrieve it. For instance, a schema for what a typical classroom looks like might include desks, a teacher's desk, a whiteboard, and students in such an environment. This expectation helps us quickly understand and navigate new classrooms without needing to analyze...
84
Working Memory
160
Working memory refers to a combination of components, including short-term memory and attention, that allow an individual to hold information temporarily as we perform cognitive tasks. It is an essential cognitive function that enables the execution of complex tasks such as problem-solving, comprehension, and reasoning. Unlike short-term memory, which simply involves the storage of information for a brief period, working memory involves the active manipulation and processing of this...
160
Higher Mental Functions of the Brain: Language
805
Language is a system of communication that allows the expression of thoughts, ideas, and feelings. The brain processes language in both hemispheres.
Language formation and comprehension take place in the dominant hemisphere. The dominant hemisphere is responsible for understanding the meaning of spoken, written, or sign language, as well as the ability to communicate. For most people, the left hemisphere is the dominant one. The right hemisphere, then, gives tone and emotional context to the...
Language formation and comprehension take place in the dominant hemisphere. The dominant hemisphere is responsible for understanding the meaning of spoken, written, or sign language, as well as the ability to communicate. For most people, the left hemisphere is the dominant one. The right hemisphere, then, gives tone and emotional context to the...
805
Chunking and Rehearsal in Sensory Memory
206
Improving short-term memory can be achieved through techniques like chunking and rehearsal. Chunking involves organizing information into larger, more manageable units. This technique is particularly useful for information that exceeds the typical memory span of between five and nine items. For instance, logging into an online account with a password like "ta89vq0179gz" involves grouping letters and numbers into three chunks—ta89, vq01, and 79gz. It makes large amounts of...
206


