Tagged articles
multi-agent system
30 articles · Page 1 of 1
This article details a multi-agent platform called Map Road Digital Employee that automates map road network data analysis, reducing case processing time from 20-30 minutes to 3-5 minutes through a four-layer agent architecture, skill-based tooling, state-machine orchestration with human-in-the-loop, and checkpoint persistence, achieving 6-10x efficiency gains while maintaining reliability.
LLM orchestrationcheckpoint persistencehuman-in-the-loop
0 likes · 25 min read

iQIYI built a Big Data Assistant using an Agent Team architecture where a Coordinator delegates tasks to domain-specific Service Agents (Scheduling, Spark, Flink, ML, Data Lake, StarRocks) that collaborate via a shared blackboard to diagnose cross-service issues, evolving from rule-based workflows to LangGraph-based agents with Harness engineering for context management, tool control, and observability.
Agent TeamCross-Service DiagnosisHarness Engineering
0 likes · 21 min read

This article dissects the Manus AI agent, revealing its three-engine architecture—planning, execution, and verification—that enables end-to-end task automation, delivering tangible outputs like reports and code instead of just conversational responses, while highlighting its reliance on external models and data limitations.
AI agentAI product designManus
0 likes · 13 min read

DoGNAVY achieved a 90.84% verification rate and placed third on the CyberGym AI‑security leaderboard by leveraging the open‑source GLM‑5.2 model within a multi‑agent workflow that combines reachability analysis, dynamic testing, independent review, and a strict sandbox environment.
AI securityAgentDoGCyberGym benchmark
0 likes · 14 min read

The talk details a multi‑agent system for AI video creation that tackles orchestration uncertainty, fault irrecoverability, and quality attribution by applying a "constrained autonomy" principle, implementing a six‑layer architecture, high‑concurrency optimizations, comprehensive observability, and layered quality gates to support hundreds of thousands of simultaneous creators.
AI Video GenerationAgentic ArchitectureQuality Gatekeeping
0 likes · 12 min read

The Robin multi‑agent system combines literature mining, hypothesis generation, and experimental data analysis into a continuous AI‑driven workflow, integrating 550 papers in 30 minutes, benchmarking on the BixBench suite, and uncovering a ROCK‑inhibitor and the glaucoma drug Lipasudil as promising treatments for dry‑age‑related macular degeneration.
automated hypothesis generationbiomedical AIdAMD
0 likes · 14 min read

The article details a multi‑agent AI system that transforms manual short‑video creation for cross‑border e‑commerce PPC campaigns into a deterministic, high‑throughput production line, describing its evolution through three phases, the underlying foundation models, modular agent roles, quality‑control mechanisms, and a self‑improving feedback loop.
AI Video GenerationPPC advertisingautomation
0 likes · 9 min read

This step‑by‑step guide shows how to create a specialized four‑agent system—research, production, quality, and distribution—coordinated by an orchestrator, using Claude and Claude Code, with detailed folder structures, prompt templates, CLI commands, and workflow automation to achieve high‑quality content output in a weekend.
AI AgentsClaudeContent Workflow
0 likes · 24 min read

Career‑Ops is an open‑source, Claude‑Code‑powered multi‑agent CLI that automates the entire job‑search pipeline—from job‑post scanning and resume generation to interview preparation and progress tracking—dramatically reducing manual effort and improving application success rates.
AICLIJob Search Automation
0 likes · 15 min read

AI Scientist‑v2, an open‑source multi‑agent system that uses progressive agent tree search to generate hypotheses, run experiments, analyze data, and write papers, has produced the first AI‑written peer‑reviewed article while highlighting both its groundbreaking capabilities and associated security risks.
AI scientistagent tree searchautomated discovery
0 likes · 7 min read

The article demonstrates how a monolithic LLM struggles with multi‑dimensional market analysis and shows, through step‑by‑step code, how assembling specialized AI agents for news, technical and financial analysis yields clearer structure, deeper insight, and higher evaluation scores.
AI ArchitectureLLM EvaluationLangChain
0 likes · 17 min read

This article provides a comprehensive, structured overview of AI agents, covering their fundamental definitions, core architecture (LLM, planning, memory, tool use), evolution from chatbots, the ReAct reasoning framework, multi‑agent systems, safety challenges like hallucination and prompt‑injection, and practical strategies for production‑grade deployment.
AI agentReactlarge language model
0 likes · 16 min read


LouZaiMar 20, 2026 · Artificial Intelligence
The article walks through the author's step‑by‑step design and deployment of a layered, multi‑agent personal AI system using OpenClaw, covering problem motivation, role decomposition, implementation pitfalls, and concrete examples such as health tracking and knowledge management.
OpenClawPersonal AIagent architecture
0 likes · 7 min read


SuanNiMar 16, 2026 · Artificial Intelligence
OpenMAIC is an open‑source AI platform that automatically converts a user‑provided topic or document into a complete interactive classroom with slides, quizzes, simulations, and multi‑agent collaboration, offering low‑cost, scalable education demonstrated by extensive trials at Tsinghua University.
AI EducationInteractive LearningOpenMAIC
0 likes · 10 min read

TiMi is a reasoning‑driven multi‑agent framework that decouples strategy development from minute‑level deployment, leverages LLMs for semantic analysis, code generation and mathematical reasoning, and achieves stable profits, high execution efficiency and strong risk control across more than 200 stock and crypto trading pairs.
LLMRisk ControlTiMi
0 likes · 17 min read

This article introduces PaperBanana, a multi‑agent AI framework that automates the creation of academic illustration by retrieving references, planning descriptions, styling, visualizing, and iteratively refining images, and evaluates its performance on the new PaperBananaBench benchmark against existing baselines.
AI illustrationBenchmarkacademic graphics
0 likes · 8 min read

This article details Alibaba‑Mama’s AI‑coding initiative, describing how a decoupled CommonAds architecture and a multi‑agent framework called “Yuanfang” transform large‑scale advertising engine development by integrating AI‑friendly design, context‑driven specifications, and automated code‑generation, testing, and validation pipelines.
AI codingCommonAdsiflow-cli
0 likes · 16 min read

This technical report details JoyCode Agent’s end‑to‑end pipeline that couples patch generation with fail‑to‑pass and pass‑to‑pass test creation, uses trajectory compression, CSR similarity retrieval, and multi‑agent iterative retries to achieve a 74.6% Pass@1 score on the SWE‑bench Verified benchmark while cutting compute costs by 30‑50%.
AI code repairPatch GenerationSWE-bench
0 likes · 38 min read

Xiaomi and Shanghai Jiao Tong University introduced DeepLight, an AI‑driven large‑model for lightweight alloys, together with the AgentMat multi‑agent framework that accelerates the full design cycle tenfold, and the LightAlloy‑Bench benchmark where DeepLight outperforms DeepSeek‑V3 and GPT‑4o by about 20 %.
AIBenchmarkLightweight Alloys
0 likes · 8 min read

Amazon Bedrock AgentCore Runtime has added native support for the Agent‑to‑Agent (A2A) protocol, enabling AI agents built with different frameworks to discover each other, share capabilities, and collaborate securely across cloud and edge environments, with a step‑by‑step guide and a real‑world monitoring use case.
A2A ProtocolAI AgentsAgentCore Runtime
0 likes · 21 min read

This article details a multi‑agent AIOps solution built on the Dify platform that automates fault detection, root‑cause analysis, and incident reporting by integrating metrics, logs, and trace data, dramatically reducing mean time to detect and resolve complex cloud‑native service failures.
AIOpsDifyMCP
0 likes · 41 min read

JoyCode Agent leverages a multi‑agent, patch‑and‑test co‑generation framework with iterative validation, failure attribution, and experience‑driven retries to achieve a 74.6% Pass@1 rate on the SWE‑Bench Verified benchmark, dramatically reducing computational resources while delivering high‑quality code patches.
AI code generationSWE-benchautomated patching
0 likes · 34 min read

QuantAgent introduces a multi‑agent LLM framework that replaces text‑based inputs with raw OHLC price signals, decomposes trading decisions into Indicator, Pattern, Trend, Risk, and Decision agents, and achieves substantially higher direction accuracy and returns across ten financial assets in zero‑shot HFT experiments.
LLMfinancial AIhigh-frequency trading
0 likes · 10 min read

The paper introduces TradingGroup, a five‑agent LLM‑based quantitative trading framework that incorporates a self‑reflection mechanism, dynamic risk management, and an automated data‑synthesis pipeline, and demonstrates superior cumulative returns, Sharpe ratios, and lower drawdowns than rule‑based, ML, RL, and existing LLM strategies on five real‑world stock datasets.
Data SynthesisLLMfinancial AI
0 likes · 14 min read

JoyAgent‑JDGenie, an open‑source, product‑grade multi‑agent system from JD Cloud, offers a fully‑featured, lightweight, end‑to‑end AI platform with model, tool, memory, agent, and application layers, allowing developers to launch a customized enterprise AI application in just five minutes, deployable locally or via Docker.
AIJavadeployment
0 likes · 6 min read

The article analyzes why production‑grade multi‑agent systems are essential for complex vertical domains, outlines their core benefits, identifies key engineering challenges such as orchestration, context handling, and tool integration, and proposes a practical entry‑level architecture with concrete design guidelines and takeaways.
AI AgentsContext ManagementVertical Industry
0 likes · 15 min read

This tutorial walks through why Multi‑Agent Systems, Anthropic's MCP and Google's A2A protocol are crucial for Agentic AI, then demonstrates how to set up two MCP servers, create a hierarchical trio of agents, enable inter‑agent coordination via A2A, and run the complete pipeline with detailed Python code and deployment tips.
A2AADKAgent Card
0 likes · 26 min read


ArchitectMar 6, 2025 · Artificial Intelligence
Manus is a general‑purpose AI agent that bridges thought and action through a multi‑agent architecture comprising planning, memory, and tool‑use modules, enabling autonomous task decomposition, execution, and result delivery across diverse scenarios such as travel planning, financial analysis, and education support.
AI agentAutonomous Planningmemory management
0 likes · 15 min read

Baidu’s Commercial Advertising Platform employs a multi‑agent architecture that combines large‑ and small‑model collaboration, SOP‑driven task decomposition, and long‑term memory to transform natural‑language queries into precise, personalized advertising actions, achieving up to 98.5% parsing accuracy and cutting analysis time from over 30 minutes to under one minute.
AI agentBaiduErnie Bot
0 likes · 17 min read

This article details the design and implementation of an LLM‑driven multi‑agent AI customer‑service assistant for vehicle selection at HuoLala, covering system architecture, algorithmic solutions, retrieval‑augmented generation, NLU/NLG agents, performance improvements, and future outlooks.
AI Customer ServiceLLMRAG
0 likes · 12 min read
