Detailed Explanation of RAG 2.0 Architecture The so-called RAG, short for Retrieval-Augmented Generation, combines retrieval and generation technologies to enhance the effectiveness of text generation tasks. Its working principle combines the advantages of retrieval models and generation models to address some challenges and issues in text generation. RAG 2.0, on the other hand, is an … Read more
Abstract The RAG system is gradually revolutionizing our understanding of AI-driven information processing. To fully leverage its potential, understanding its fundamental principles is crucial. This article aims to succinctly analyze the RAG system, hoping to provide insights and resonance for readers. What is the RAG System? In short, the RAG system integrates large language models … Read more
Comparison table Aspect MiniMax-01 DeepSeek-V3 Model Architecture Based on linear attention mechanism, using a hybrid architecture (Hybrid-Lightning), and integrating MoE architecture. Based on Transformer architecture, using MLA and DeepSeekMoE architectures, and introducing auxiliary loss-independent load balancing strategies. Parameter Scale 456 billion total parameters, 45.9 billion active parameters. 671 billion total parameters, 37 billion active parameters. … Read more
Personal Opinion: The commercial hype around intelligent agents is currently rampant, but there are very few “killer applications” that have landed successfully. I believe the main reason is that the application direction of intelligent agents has gone astray. Large language models are probabilistic models, and applying a single intelligent agent in a scenario with high … Read more
(Source: MIT Technology Review) AI agents are currently a hot topic in the tech field. From Google DeepMind and OpenAI to Anthropic, major companies are competing to give LLMs the ability to autonomously complete tasks. These systems are referred to as Agentic AI and have become a new focal point of discussion in Silicon Valley. … Read more
Today, let’s take a look at a classic agent work from Princeton, Google Brain, and others published at 2023 ICLR – ReAct. Project address: https://github.com/ysymyth/ReAct?tab=readme-ov-file Research motivation: Although existing large language models excel in language understanding and interactive decision-making, their reasoning and action capabilities are often studied separately. Currently, the most famous work on reasoning … Read more
In today’s rapidly advancing technological era, the term “intelligent agent” has gradually entered the public eye, becoming a hot topic of discussion. So, what exactly is an intelligent agent? An intelligent agent, known in English as an AI Agent, is a system that mimics human intelligent behavior. It is like a “smart brain” with rich … Read more
In this age of information explosion, tutorial writing has become an important skill. Whether it’s technical sharing, knowledge dissemination, or education and training, high-quality tutorials can bring great value to users. Today, we will teach you step by step how to create a tutorial writing agent using the Zigent framework, allowing it to automatically generate … Read more
Source | BLUES, Intelligent Gorilla This article is the speech given by Andrew Ng in March this year, titled “Agentic Reasoning”, which explains the trends in AI agent workflows. This article translates AI agents as AI proxies. This article is for academic/technical sharing only. If there is any infringement, please contact us to delete the … Read more
Guest | Li Li, Head of PingCAP AI Lab Editor | Li Zhongliang In the face of increasing data volumes, complex business logic, and the pursuit of higher performance and reliability, database systems face numerous challenges. One of the current issues to be addressed is the effective handling of large-scale data while ensuring data security … Read more