AI Agent

Research on Cross-Media Intelligence with Large and Small Model Collaboration

by
Research on Cross-Media Intelligence with Large and Small Model Collaboration

Written by/Zhuang Yueting This article is divided into four parts: first, the research background and content; second, the introduction of the current two research approaches; third, the research foundation and progress made; and finally, the conclusion and outlook. 1 Research Background and Content Currently, large models/multi-modal large language models (LLM/MLLM) have reached new heights in … Read more

Three Agents Equal One GPT-4: A Collaborative Framework Based on Open Source Models

by
Three Agents Equal One GPT-4: A Collaborative Framework Based on Open Source Models

MLNLP community is a well-known machine learning and natural language processing community both domestically and internationally, covering NLP graduate students, university teachers, and researchers from enterprises. The Community’s Vision is to promote communication and progress between the academic and industrial fields of natural language processing and machine learning, especially for the progress of beginners. Reprinted … Read more

Summary of Various GPT-4 Autonomous Systems: AutoGPT, AgentGPT, BabyAGI, HuggingGPT, CAMEL

by
Summary of Various GPT-4 Autonomous Systems: AutoGPT, AgentGPT, BabyAGI, HuggingGPT, CAMEL

Source: Deephub Imba This article is approximately 1400 words long and suggests a reading time of 5 minutes. Integrating ChatGPT and LLM into various applications is just part of the potential of using language models. The emergence of ChatGPT and LLM technology has swept the world with these state-of-the-art language models, prompting not only AI … Read more

War or Peace? Multi-Agent System Simulation of World War Outbreak Based on Large Language Models

by
War or Peace? Multi-Agent System Simulation of World War Outbreak Based on Large Language Models

Introduction Can we avoid war at the crossroads of history? Individuals, scholars, policymakers, and organizations throughout human history have been pursuing this question. In the field of complex systems research, simulating the process of war through techniques such as wargaming and multi-agent simulation has been a long-standing topic. Especially driven by the transformative power of … Read more

Professor’s View | Wei Hang: Is GPT+Meta the Intelligent Factory of Future Business Education?

by
Professor's View | Wei Hang: Is GPT+Meta the Intelligent Factory of Future Business Education?

SUFE MBA/EMBA On December 19, 2024, the “2024 International Online Education Conference” hosted by the China Central Radio and Television Station and organized by Genesis Blue Ocean was successfully held in Beijing. The theme of this conference is “Empowering Education with Technology to Shape the Future”, bringing together authoritative experts in education, renowned principals, and … Read more

MetaGPT Open-Source Auto-Generated Agentic Workflow

by
MetaGPT Open-Source Auto-Generated Agentic Workflow

MLNLP community is a well-known machine learning and natural language processing community both domestically and internationally, covering NLP master’s and doctoral students, university teachers, and corporate researchers. The vision of the community is to promote communication and progress between the academic and industrial circles of natural language processing and machine learning at home and abroad, … Read more

Decoding LLM Application Framework: DSPy

by
Decoding LLM Application Framework: DSPy

In the past six months, I have been continuously engaged in development work related to LLM applications. However, as many may have noticed, there haven’t been many “cognitive-refreshing” technological or application changes lately, so I haven’t had enough enthusiasm to write new articles. Model Progress From the model perspective, since the release of GPT-4 in … Read more

How Google Gemini Achieves Smart Interaction Through Language Models

by
How Google Gemini Achieves Smart Interaction Through Language Models

Introduction: This article aims to explore an innovative path by utilizing Google’s Gemini Flash instead of the widely known LangChain to achieve intelligent interaction with CSV files. We will build a simple CSV interpreter that generates code and parses data without LangChain, creating an intuitive user interface with Streamlit.©️【Deep Blue AI】 In today’s rapidly evolving … Read more

What Unique Techniques Did OpenAI Use in the o1 Model?

by
What Unique Techniques Did OpenAI Use in the o1 Model?

Book Giveaway at the End Part.1 OpenAI o1: The AI Model Beyond Human PhDs Recently, OpenAI made a significant announcement, launching the new large model o1, which once again shocked the industry. The o1 model has demonstrated exceptional capabilities in a series of challenging benchmark tests, with reasoning abilities that can even surpass human experts … Read more

Latest ReWOO Framework Addresses Auto-GPT and LangChain Redundancy

by
Latest ReWOO Framework Addresses Auto-GPT and LangChain Redundancy

MLNLP community is a well-known machine learning and natural language processing community both domestically and internationally, covering NLP master’s and doctoral students, university professors, and corporate researchers. The vision of the community is to promote communication and progress between the academic and industrial sectors of natural language processing and machine learning, especially for beginners. With … Read more