自然语言编程(NLPg):生成式 AI 时代对语言、记忆与认知的再思考
Natural Language Programming: Rethinking Language, Memory, and Cognition in the Era of Generative AI
AI 导读
一篇 arXiv 论文提出自然语言编程(NLPg)概念,将大语言模型时代的提示词视为外化目标、约束与推理状态的动态认知工件,而非单纯的技术交互手段。论文基于分布式认知、扩展心智与元认知理论,提出“对话式工作记忆”框架,并将 BTMA、SKGE、RMR 等记忆架构映射到该框架,说明情景、语义与元认知层如何支撑长程对话连贯性。
正文 · 原文
Abstract:Generative Artificial Intelligence is transforming the role of natural language in computational systems. In classical Natural Language Processing (NLP), language was treated as an object of computation: something to analyse, classify, translate, or generate. Large Language Models (LLMs) challenge this perspective, enabling natural language to function increasingly as an executable cognitive medium through which humans structure reasoning, orchestrate problem solving, and regulate hybrid human/AI workflows.
This paper introduces Natural Language Programming (NLPg) as a theoretical and epistemological extension of traditional NLP. Rather than focusing on language understanding alone, NLPg conceptualises prompts as dynamic cognitive artefacts that externalise goals, constraints, assumptions, validation criteria, and intermediate reasoning states. Prompting is thus not merely a technical interaction technique, but a form of dialogic cognitive programming operating within distributed human/AI memory architectures.
Building on theories of distributed cognition, extended mind, metacognition, and dialogic learning, the paper proposes the notion of Dialogic Working Memory, describing how prompts and conversational states function as temporary external memory structures supporting reasoning continuity and reflective regulation. We further map existing memory architectures (BTMA, SKGE, RMR) onto this framework, illustrating how episodic, semantic, and metacognitive layers support long-horizon conversational coherence.
Finally, implications for computational linguistics and AI/mediated knowledge systems are discussed, suggesting a post symbolic and post interface paradigm in which natural language operates simultaneously as communication medium, executable specification, cognitive scaffold, and distributed memory architecture.
| Comments: | 11 pages, 1 figure, 2 tables |
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| MSC classes: | 68T50 (Primary), 68T01, 68T30 (Secondary) |
| ACM classes: | I.2.7; H.5.2; I.2.0 |
| Cite as: | arXiv:2611.23106 [cs.CL] |
| (or arXiv:2611.23106v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23106 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Giovanni Adorni [view email]
[v1]
Tue, 17 Nov 2026 17:27:01 UTC (45 KB)
来源:arXiv cs.AI · arxiv.org