生成式AI第二幕：测试时扩展推动认知工程

摘要

第一代大型语言模型——可称为生成式AI的“第一幕”（2020-2023年）——通过海量参数与数据扩展取得了显著成就，但在知识时效性、浅层推理及受限认知过程方面仍存在根本性局限。这一时期，提示工程（Prompt Engineering）成为我们与AI交互的主要界面，实现了基于自然语言的对话级沟通。如今，我们正见证“第二幕”（2024年至今）的兴起，模型正通过测试时扩展技术从（潜在空间中的）知识检索系统向思维构建引擎转型。这一新范式通过基于语言的思维与AI建立了心智层面的连接。本文中，我们明确了认知工程的概念基础，并阐释了为何当前是其发展的关键时期。我们通过全面教程与优化实现系统性地拆解这些先进方法，使认知工程普及化，让每位从业者都能参与到AI的第二幕中。我们在GitHub仓库中持续更新了关于测试时扩展的论文合集：https://github.com/GAIR-NLP/cognition-engineering。

English

The first generation of Large Language Models - what might be called "Act I" of generative AI (2020-2023) - achieved remarkable success through massive parameter and data scaling, yet exhibited fundamental limitations in knowledge latency, shallow reasoning, and constrained cognitive processes. During this era, prompt engineering emerged as our primary interface with AI, enabling dialogue-level communication through natural language. We now witness the emergence of "Act II" (2024-present), where models are transitioning from knowledge-retrieval systems (in latent space) to thought-construction engines through test-time scaling techniques. This new paradigm establishes a mind-level connection with AI through language-based thoughts. In this paper, we clarify the conceptual foundations of cognition engineering and explain why this moment is critical for its development. We systematically break down these advanced approaches through comprehensive tutorials and optimized implementations, democratizing access to cognition engineering and enabling every practitioner to participate in AI's second act. We provide a regularly updated collection of papers on test-time scaling in the GitHub Repository: https://github.com/GAIR-NLP/cognition-engineering

生成式AI第二幕：测试时扩展推动认知工程

Generative AI Act II: Test Time Scaling Drives Cognition Engineering

摘要

Summary

Support

Support