In-Depth Insights: A Guide to Key Development Trends of AI Agents in 2024

In-Depth Insights: A Guide to Key Development Trends of AI Agents in 2024

Today’s AI agents are capable of perceiving, making decisions, and taking actions independently. With the rise of large language model (LLM)-driven AI agents, we are on the brink of a new era: AI agents may form their own societies and coexist harmoniously with humans. Below, we will discuss what AI agents are, why they are … Read more

Understanding the Boundaries of Intelligence: Do Large Language Models Have Agency?

Understanding the Boundaries of Intelligence: Do Large Language Models Have Agency?

Click Follow us by clicking the blue text aboveCover Image:True “Agentic AI” requires intrinsic motivation, predictive models of the world, and sociality. β€œ 𝕀²·ℙaradπ•šgπ•ž Intelligent Square Paradigm Research: Writing Deconstructs Intelligence, Paradigm Enhances Cognition Current large language models (LLMs), despite exhibiting astonishing intelligence, do not possess true “agency”. The behaviors we perceive as LLM “agents” … Read more

What is an AI Agent? Exploring the Intersection of Artificial Intelligence and LLMs

What is an AI Agent? Exploring the Intersection of Artificial Intelligence and LLMs

Artificial Intelligence (AI) is spreading at an astonishing rate, like wildfire across the grasslands. In this field, Large Language Models (LLM) have emerged as a focal point of attention. Meanwhile, the concept of AI Agent is rising like a new star, sparking widespread discussion throughout the tech community and society at large. Industry experts and … Read more

A Comprehensive Review of the Technological Evolution of Large Multimodal Reasoning Models: From Modular Architectures to Native Reasoning Capabilities

A Comprehensive Review of the Technological Evolution of Large Multimodal Reasoning Models: From Modular Architectures to Native Reasoning Capabilities

This study systematically reviews and analyzes the technological development of Large Multimodal Reasoning Models (LMRMs). It outlines the evolution of the field from early modular, perception-driven architectures to unified, language-centric frameworks, and introduces the cutting-edge concept of Native Large Multimodal Reasoning Models (N-LMRMs). The paper constructs a structured roadmap for the development of multimodal reasoning, … Read more

The Evolution of AI Agents: From RL-Driven to Large Model-Driven | AIR 2025

The Evolution of AI Agents: From RL-Driven to Large Model-Driven | AIR 2025

MLNLP community is a well-known machine learning and natural language processing community both domestically and internationally, covering audiences including NLP graduate 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.Source | New … Read more

Why LoRA Has Become an Indispensable Core Technology for Fine-Tuning Large Models?

Why LoRA Has Become an Indispensable Core Technology for Fine-Tuning Large Models?

In the field of artificial intelligence, large language models (LLMs) such as Claude, LLaMA, and DeepSeek are becoming increasingly powerful. However, adapting these models to specific tasks, such as legal Q&A, medical dialogues, or internal knowledge queries for a company, traditionally involves “fine-tuning” the model. This often entails significant computational overhead and high resource costs. … Read more

Tina: A Lightweight Inference Model Based on LoRA

Tina: A Lightweight Inference Model Based on LoRA

How can we achieve strong inference capabilities in language models at a low cost? Driven by this fundamental question, we propose Tina β€” a family of lightweight inference models realized with high cost efficiency. Tina demonstrates that significant improvements in inference performance can be achieved even with minimal resources. This achievement is realized through the … Read more

Leading the Future Smart Revolution: A Comprehensive Analysis of AI Agent Technology Development

Leading the Future Smart Revolution: A Comprehensive Analysis of AI Agent Technology Development

In the field of artificial intelligence, with the rise of large language models (LLMs), AI Agents are becoming the most notable technology hotspot of 2025. Unlike ordinary AI applications, AI Agents possess the ability to think independently, perceive their environment, and execute complex tasks, reshaping our understanding of artificial intelligence. This article will provide a … Read more

Implementation of Function Call Based on RK3588 Large Language Model

Implementation of Function Call Based on RK3588 Large Language Model

The example of function call invocation is as follows: POST /v1/chat/completions HTTP/1.1 Host: api.openai.com Authorization: Bearer YOUR_API_KEY Content-Type: application/json { "model": "gpt-4", "messages": [{"role": "user", "content": "What is the weather like in Beijing today?"}], "tools": [ // Define the tool list { "type": "function", "function": { "name": "get_weather", "description": "Get weather information for a specified … Read more

RK3588-Based rkllm Compatible with OpenAI API

RK3588-Based rkllm Compatible with OpenAI API

Usage: git clone https://github.com/huonwe/rkllm_openai_like_api.gitcd rkllm_openai_like_api Add the required dynamic libraries: sudo cp lib/*.so /usr/lib Installuv: curl -LsSf https://astral.sh/uv/install.sh | sh Installpythondependencies: uv sync Run: uv run server.py By default, the platform is set to rk3588, the model path is models/deepseek-r1-1.5b-w8a8.rkllm, and the listening port is 8080. You can manually specify parameters, such as uv run … Read more