This article breaks down an AI agent's workflow—perception, planning, action, and memory—using a product‑launch example, explains reasoning methods like Chain‑of‑Thought and ReAct, details tool integration, memory types, common failure modes, and why planning and tool ecosystems are essential.
An AI Agent is a large‑model system that can perceive its environment, plan steps, invoke tools, and remember past interactions to autonomously achieve user‑specified goals, distinguishing it from simple chatbots that only answer questions.
This article introduces the Tree of Thoughts (ToT) reasoning framework, explains its search‑tree based workflow, demonstrates a full implementation with LangGraph to solve the classic wolf‑goat‑cabbage puzzle, and compares its reliability against a simple Chain‑of‑Thought approach.
The article analyzes Matt Van Horn’s workflow that replaces traditional IDEs with a planning‑first approach using markdown task files, voice input, parallel research agents, and a custom "last30days" engine, showing how AI can orchestrate research, planning, execution, and verification to boost productivity across code and non‑code tasks.
The article explains AI agents as autonomous systems that perceive environments, plan, use tools, iterate through action loops, and self‑reflect, contrasting them with traditional chatbots and workflows, and outlines their core abilities, memory types, tool‑use mechanisms, and single‑ versus multi‑agent architectures.
This article breaks down the concept of AI agents for interview preparation, covering their definition, core components like planning, memory, and tool use, differences from plain LLM chats, real‑world challenges, typical use cases, detailed component analysis, and a runnable pseudo‑code example.
The article explains why an AI Agent is more than a simple LLM API call, outlines its four essential modules—memory, planning, tool use, and feedback—shows how they differ from ordinary models, and offers practical steps and common pitfalls for building a production‑grade single‑agent system.
The article explains the four essential components of AI Agents—brain, memory, tool, and planning layers—illustrates their implementation with Python code, compares planning strategies, shares a real-world OOM fault‑diagnosis case, and lists common pitfalls to help newcomers build functional agents.
The article analyzes why autonomous LLM agents become expensive, breaks down their cost components, and presents concrete engineering strategies—memory management, tool‑call optimization, and planning constraints—to dramatically reduce token usage and improve reliability while maintaining performance.
A joint survey by nine leading Chinese institutions outlines the efficiency crisis of modern AI agents and proposes three strategic directions—efficient memory, tool learning, and planning—detailing concrete mechanisms, representative models, and emerging trends for building high‑performing, low‑cost agents.
Google DeepMind's new "Intrinsic Self‑Critique" method lets large language models iteratively self‑evaluate and rewrite their plans, raising Blocksworld planning accuracy from 49.8% to 89.3% and setting new records across multiple planning benchmarks.
Cursor ran a team of AI coding agents for a week to build a prototype browser, uncovering three major failure modes—drift, collaboration breakdown, and lack of quality signals—and proposing a planner/worker split plus eight concrete tactics that ordinary developers can adopt for long‑running autonomous coding tasks.
This article explains the fundamental architecture of reinforcement learning, contrasting model‑free and model‑based approaches, detailing environment models, planning, data augmentation, expert iteration, and embedding planning, and then examines how large language models use policy‑based methods such as PPO, DPO, and GRPO for RL‑HF.
This article explores how to create a self‑thinking AI data analyst by detailing agent fundamentals, core modules such as planning, memory and tool scheduling, practical development steps, multi‑agent collaboration, evaluation benchmarks, and real‑world examples like stock backtesting.
This article explains why most LLM‑based agents only perform pseudo‑planning through prompts or hard‑coded loops, outlines when to rely on prompt‑driven versus program‑driven planning, compares popular frameworks such as ReAct, MRKL, BabyAGI and AutoGPT, and clarifies what true autonomous planning would require.
This article explains AI Agents by contrasting them with traditional AI tools, detailing their official definition, core components—planning, tool use, memory, action—illustrating a travel‑planning example, outlining agent types, and highlighting their significance for AGI and real‑world applications.
This article reveals why many businesses struggle with supply‑chain efficiency and explains how focusing on four critical links—planning, inventory management, logistics, and receivables—can transform operations, reduce costs, and improve customer satisfaction, offering practical examples and a downloadable template for immediate implementation.
This article explains how to improve supply chain performance by focusing on critical indicators—delivery reliability, compliance, forecast accuracy, production load balance, inventory turnover, timeliness, cost proportion, and receivable aging—rather than merely tracking superficial numbers.
Learn why many companies suffer from excess inventory yet material shortages, and follow a step‑by‑step procurement planning framework—collecting demand, expanding BOM, calculating net needs, scheduling based on lead times, and continuously adjusting—to keep stock balanced, avoid production delays, and optimize supply chain efficiency.
This article explains what an AI agent is, outlines its four core modules—perception, memory, planning, and action—describes the role of large language models, compares software development generations, discusses memory implementations, planning methods like ReAct and Plan‑and‑Solve, and covers evaluation, cost analysis, and differences between agents and workflows.
JD.com’s Genie open‑source AI agent introduces eight powerful capabilities—including plug‑in multi‑agent support, iterative planning, cross‑task context sharing, digital employee enhancements, deep model‑plus‑search, CodeTool for code lifecycle, refined system prompts, and a configurable MCP server—designed to boost intelligent workflow efficiency.
An extensive review introduces a taxonomy for integrating graph techniques with AI agents, detailing how graphs enhance core functions such as planning, execution, memory, and multi‑agent coordination, and discusses representative applications, challenges, and future research directions.
This article reveals why procurement is often underestimated, outlines the three essential capabilities—planning, collaboration, and cost control—and provides a step‑by‑step framework for creating effective purchase plans, aligning with production, sales, and R&D, and mastering total‑cost management to boost company profitability.
This article examines Copilot 3.0’s planning module, explains how DeepSeek R1’s GRPO reinforcement‑learning pipeline enables flexible multi‑agent orchestration, addresses the limitations of Copilot 2.0, and presents experimental results that show a 61% reduction in reasoning length and a 9% relative gain in accuracy.
This article surveys the rapid emergence of AI agents, outlining their projected 2025 breakthrough, market momentum, key frameworks such as Manus and MCP, the four core abilities of perception, planning, tool use, and memory, and the evolving landscape of multimodal and autonomous AI systems.
This article combines theoretical analysis and practical case studies to systematically explore the core components, design patterns, and future directions of AI agents, detailing the implementation of OpenManus, custom memory and planning modules, experimental evaluations, and insights for improving agent reliability and scalability.
This guide explains why projects often fail, defines project management, and walks through the five essential phases—initiation, planning, execution, monitoring, and closure—providing practical steps, key metrics, and visual tools to help teams deliver results on time, within budget, and with quality.
Professor Li Hongyi’s lecture provides a comprehensive, step‑by‑step exploration of AI agents, covering their definitions, reinforcement‑learning roots, LLM integration, memory mechanisms, tool usage, planning strategies, benchmarks, and practical examples, offering a valuable resource for anyone studying modern artificial intelligence.
The article explains what AI Agents are, how they differ from single large‑model systems, outlines four agent architectures—Reflection, Tool Use, Planning, and Multi‑Agent—and cites concrete examples from Grammarly, VS Code plugins, Image Describer X, ChatDev, as well as initiatives by Tencent and Google, highlighting the 2025 AI Agent boom.
This article explains how a mixed‑integer programming tool developed by ByteDance's SYS‑DCD team integrates cost, reliability, delivery speed, and environmental metrics to optimize data‑center planning, reduce power waste, and accelerate deployment across multiple regional scenarios.
This article explains how to differentiate goals from plans, align objectives with strategy using SMART and OKR principles, apply Work Breakdown Structure (WBS) to break down goals into concrete actions, and use time‑management techniques like the Eisenhower matrix for effective execution.
JD’s Merchant Intelligent Assistant leverages a large‑language‑model‑based multi‑agent architecture to provide 24/7 e‑commerce support, detailing its evolution, planning techniques, online inference, evaluation methods, sample generation, and practical insights for scalable AI‑driven operations.
This article explains what LLM agents are, their core components—brain, memory, planning, and tool use—illustrates how they handle complex queries through task decomposition, surveys notable frameworks, and discusses key challenges such as limited context, long‑term planning difficulties, output inconsistency, and prompt dependence.
The article examines current limitations of AI agents in planning and complex reasoning, critiques existing methods like COT/TOT and ReAct, and proposes practical strategies—including combined COT‑Reflection approaches, structured memory algorithms, and white‑box interaction designs—to enhance agent performance within the DataFun knowledge map framework.
The article outlines the rapid progress of LLM agents in 2024 while highlighting key difficulties in planning capabilities, evaluation methods, dataset generation, and metric design, and suggests practical combinations and product‑level enhancements to improve efficiency, accuracy, and usability.
This article shares practical advice for novice project managers, covering the four process groups—initiation, planning, execution, and monitoring—through real‑world examples, stakeholder identification, risk handling, change control, and communication techniques to help them deliver value and grow their teams.
This article surveys the design of autonomous large‑language‑model agents, detailing their modular architecture—including profiling, memory, planning, and execution—while also reviewing common profiling methods, memory structures, planning techniques, action strategies, and various learning approaches such as exemplar, human‑in‑the‑loop, and environment‑feedback training.
This article reviews the emerging field of large language model‑based AI agents, outlining their overall architecture, key challenges such as role‑playing, memory, planning, and multi‑agent collaboration, and discusses future research directions and practical examples in user behavior simulation and software development.
This article reviews the emerging field of large‑language‑model (LLM) based AI agents, outlining their overall architecture, core modules such as profiling, memory, planning and action, discussing current challenges, presenting concrete use‑cases, and highlighting promising research directions.
AI agents extend large language models with planning, short‑term and long‑term memory, and tool‑use capabilities, enabling autonomous task decomposition, external API interaction, and persistent knowledge retrieval; frameworks such as MetaGPT, LangChain, and CrewAI simplify building agents like a researcher that gather information, browse web content, and generate reports, heralding broader AI‑enhanced productivity.
This article systematically outlines the architecture of large‑language‑model (LLM) agents, examines their key technical challenges such as role‑playing, memory design, reasoning and multi‑agent collaboration, and explores emerging research directions and practical case studies.
This article surveys the emerging field of large‑language‑model (LLM) based agents, detailing their modular architecture—including profiling, memory, planning, and action components—while discussing critical challenges such as role‑playing, memory design, reasoning, multi‑agent collaboration, and outlining promising research directions and practical case studies.
This article reviews recent advances in using large language models for embodied interactive agents, introduces the dual‑modality SwiftSage architecture that combines a fast T5‑based small model with a powerful large model for planning and grounding, and evaluates its performance on benchmarks such as ScienceWorld.
This article provides a detailed guide to cloud migration, covering evaluation and analysis, pilot projects, assessment strategies, planning and design with cloud services, verification and implementation steps, continuous measurement, and cost optimization through FinOps to ensure successful and secure migration.
The article critically examines GPT‑4 and similar transformer models, highlighting persistent hallucinations, outdated knowledge, insufficient domain coverage, lack of planning and memory, and proposes architectural extensions inspired by fast‑slow thinking and differentiable modules to overcome these fundamental constraints.
This article outlines ten essential components of project management—including overall management, scope, schedule, cost, quality, resources, communication, risk, procurement, and integration—while providing practical tips, stakeholder analysis methods, and visual guides to help teams execute projects efficiently.
This article introduces data‑to‑text generation, discusses its task background, common datasets, structured data representations, explicit and implicit planning methods, model architectures such as RNN, Transformer and VAE, and compares the advantages and challenges of each approach.
This guide explains how to plan an application by defining the problem it solves, understanding users and goals, then outlines systematic steps to analyze, improve, and automate business workflows, including practical questions, optimization methods, and a detailed expense‑report case study.
This article examines why digital transformation projects often stumble, outlining the planning logic, stages of transformation, and the roles of DevOps, cloud computing, and technology in reshaping business models, operations, and talent development, while highlighting common failure causes and practical guidance for successful implementation.
This guide presents a comprehensive, step‑by‑step framework for IT architecture governance, covering objectives, governance models, roles, processes, standards, toolchains, metrics, and an implementation roadmap to help organizations align technology decisions with business goals.
This article presents a concise collection of the most practical project management essentials, illustrated through a series of visual slides covering key techniques and tools for effective project execution.
The article outlines the common problems faced by newly promoted managers—time shortage, delegation uncertainty, unmet goals, and unmotivated subordinates—then presents a five‑unit framework covering roles, planning, organization, leadership, and control to build effective management habits.
This article explains why every team member should master planning, outlines its three core benefits—focus, insight, and future direction—introduces two thinking modes (inductive and deductive) and presents four practical planning methods to make your roadmap clear, actionable, and results‑driven.
This article explains why planning is essential for every team, outlines two core thinking modes—inductive and deductive—and shares four practical planning methods (similar‑thinking, dimensional‑thinking, reduction‑thinking, and specialization) to help practitioners create focused, actionable, and measurable roadmaps.
The article explains how Azure DevOps and Azure DevOps Server adopted agile principles, detailing team organization, cultural shifts, planning hierarchies, defect‑limit practices, and new health‑preserving methods that together improve collaboration, transparency, and delivery cadence.
This guide outlines eight practical steps—including defining scope, forming a planning team, setting clear objectives, designing realistic scenarios, creating evaluation checklists, assigning roles, conducting pre‑drill briefings, and performing post‑drill reviews—to help organizations execute effective, repeatable disaster recovery exercises that strengthen business continuity.
Drawing from years of project experience, the author outlines ten common factors—ranging from unattainable goals to inexperienced managers—that consistently lead to project failure, and suggests that even a single misstep can doom a project.
This article outlines a comprehensive plan for deploying GaussDB T, covering the software architecture, component roles, and practical guidelines for single‑node, primary‑standby, and distributed setups, while highlighting common pitfalls and operational considerations for production environments.
The article reviews the complex system model of autonomous heavy trucks, outlines traditional and modern planning and control methods—including rule‑based FSM, POMDP, learning‑based and optimization techniques—highlights safety, efficiency, fuel‑economy, and dynamic modeling challenges specific to heavy‑truck and trailer configurations, and shares practical attempts such as lane‑changing, merging, and trailer‑aware trajectory planning.
This article explores how autonomous driving systems can simultaneously ensure safety and passenger comfort by optimizing planning and control modules, defining safety and comfort metrics, formulating constraints and cost functions, and employing models such as the bicycle model for lateral and longitudinal control.
This article argues that proactive planning is more constructive than passive year‑end summaries, explains how setting clear goals, breaking them into tasks, estimating time, and using simple tools like spreadsheets and Gantt charts can improve personal and professional productivity, even amid rapid change.
The article clarifies common misconceptions about waterfall and agile, explaining that both approaches require thoughtful planning, adaptability, and value‑driven delivery rather than merely executing a fixed plan or abandoning planning altogether.
This article shares practical insights on project management, covering how to understand project goals, assess resources, communicate with stakeholders, handle risks and changes, create effective plans, and ensure successful delivery through disciplined documentation and verification.
This guide outlines sixteen practical project‑management insights—from defining clear goals and stakeholder roles to handling cost‑cutting pressures and risk mitigation—helping teams streamline planning, improve execution, and prevent unnecessary overtime.
