multi-agent

AI Coding Sprint "DeepSeek Moment": Gen Z Team Uses Domestic Model to Instantly Deliver Complex Apps, Surpassing Claude Code

AI programming

AI Coding Sprint "DeepSeek Moment": Gen Z Team Uses Domestic Model to Instantly Deliver Complex Apps, Surpassing Claude Code

Cloud-Based AI Agents: Redefining the Programming Paradigm Cloud-based AI Agents are making significant advances, transforming how software is conceived, developed, and deployed. With zero human intervention, an “AI programming team” can directly deploy complex applications, leveraging ultra-large context capacities — reaching tens of millions in scale. Imagine simply stating your requirements,

By Honghao Wang
Exploration and Practice of Building an Inclusive Finance Intelligence Hub at ICBC Software Development Center Based on Multi-Agent and MCP

inclusive finance

Exploration and Practice of Building an Inclusive Finance Intelligence Hub at ICBC Software Development Center Based on Multi-Agent and MCP

2025-11-08 12:50 Zhejiang The inclusive finance sector is facing multiple real-world challenges: * Complex business processes * Heavy information-processing workloads * Tight human resources To address these problems, the ICBC Software Development Center developed an intelligent assistant, Gong Xiaohui, powered by the MOA (Multi-Agent Orchestration) collaboration framework and the MCP (Multi-Channel Protocol)

By Honghao Wang
New LLM Reinforcement Learning Framework: UCSD Multi-Agent Training Boosts LLM Tool-Use Capability by 5.8×

LLM

New LLM Reinforcement Learning Framework: UCSD Multi-Agent Training Boosts LLM Tool-Use Capability by 5.8×

Reinforcement Learning Framework for Large Language Model Agents First Implementation of Universal Multi-Agent Group Reinforcement --- Background Numerous studies show that multi-agent workflows with large language models (LLMs) often outperform single-agent systems — even without targeted training. Yet, most current LLM agent training frameworks are limited to single-agent training, leaving universal

By Honghao Wang
Agent Workflow Framework: Efficient Management of Multi-Model Interaction and Task Allocation | Open Source Daily No.778

AI workflow

Agent Workflow Framework: Efficient Management of Multi-Model Interaction and Task Allocation | Open Source Daily No.778

openai-agents-python: A Lightweight Multi-Agent Workflow Framework GitHub Repo: openai/openai-agents-python Stars: 16.7k | License: MIT openai-agents-python is a lightweight yet powerful multi-agent workflow framework that enables flexible, vendor-independent AI solutions. Key Features * Multi-LLM Support — Works with OpenAI’s Response & Chat Completion APIs, and 100+ other LLMs for maximum flexibility.

By Honghao Wang
Efficient Integration of Multiple AI Models: Enabling Task Isolation and Role Specialization | Open Source Daily No.774

AI integration

Efficient Integration of Multiple AI Models: Enabling Task Isolation and Role Specialization | Open Source Daily No.774

zen-mcp-server: Multi-Model Context Protocol Server zen-mcp-server is a multi-model collaborative context protocol server designed to integrate multiple AI models and command-line tools, enhancing development team productivity. It enables seamless cooperation between various CLI tools and offers CLI-to-CLI bridging, allowing for task isolation, role specialization, and preserved conversational context. Repository: BeehiveInnovations/

By Honghao Wang
DeepResearch Architecture and Practice Based on Spring AI Alibaba

Spring AI

DeepResearch Architecture and Practice Based on Spring AI Alibaba

DeepResearch System Documentation 1. Introduction & Overview DeepResearch is a Java-based intelligent research automation system built with Spring AI and Alibaba Graph. It enables an end-to-end workflow — from information gathering to analysis, and finally, structured report generation. Key Capabilities * Reasoning Chain: * Automatically constructs a logical analysis process from collected materials

By Honghao Wang