Tagged articles
Tool Use
89 articles · Page 1 of 1
HKUST MMSense Lab introduces a visual-native agent framework that assigns unique IDs to images for tool chaining in multimodal deep search, and an on-policy data evolution method that iteratively refines question-generation rules using agent rollouts, boosting 8B and 30B model accuracy across eight benchmarks.
HKUST MMSense LabImage ReuseMultimodal Deep Search
0 likes · 20 min read

Anthropic's Applied AI team finds that single agents equipped with Skills outperform multi-sub-agent architectures in output quality, cost, and latency, and provides a four-step migration guide to consolidate sub-agents into a unified loop using progressive disclosure.
AI agentsAnthropicProgressive Disclosure
0 likes · 18 min read

Researchers from HKUST Guangzhou, Fudan, Washington, Imperial College, and Stanford introduce OpenDS-World, a benchmark of 200 real-world deep search tasks spanning 4 modalities, 42 resource formats, and 7 access types; 12 frontier models including GPT-6 Astra, Claude Opus 5.5, and Gemini 3.8 Flash achieve at best 39% accuracy, revealing severe challenges in long-horizon decision-making, tool failure recovery, and search termination.
AI agentsBenchmarkDeep Search
0 likes · 21 min read


ArchitectOct 28, 2026 · Artificial Intelligence
Anthropic finds that splitting AI agents by business function often increases latency due to handoff overhead; they recommend consolidating sub-agents into a main loop using four patterns — merge, fold, as-tool, keep — with Skills for business rules, tools for actions, and task-level evaluation to catch regressions.
AI agentsAgent EvaluationAnthropic
0 likes · 24 min read

The article analyzes the 2026 emergence of Personal Agents, dissecting their four-component architecture, comparing ten products including Cue, Fo, Dots, Muse, and Grok Bot, and detailing technical challenges in persistent state, memory, identity, triggers, permissions, and failure handling, concluding with a China-specific outlook on ecosystem-embedded agents and trust-based monetization.
2026 AI ProductsAI agent architectureAgent Identity
0 likes · 53 min read

This article dissects Perplexity's production system prompt for its search agent, revealing how a concise 1,000-word prompt with eight tools enforces tool-first behavior, parallel calls, a three-call limit, and direct-answer formatting to eliminate hallucination and latency.
AI agentsPerplexityTool Use
0 likes · 12 min read

This tutorial guides you through building a complete AI Agent from scratch without frameworks, covering environment setup, tool definition with JSON Schema, Function Calling, the core reasoning loop, common pitfalls, prompt engineering techniques for structured output, and modular code organization with hands-on practice tasks.
AI agentAgent DevelopmentFunction Calling
0 likes · 22 min read

This tutorial explains how AI agents use tools via Function Calling, demystifies the @tool decorator by showing how Python introspection generates OpenAI JSON schemas, provides a complete 60-line hand-written agent implementation, and outlines five golden rules for tool design including detailed docstrings, semantic parameter names, limiting tools to 20, single responsibility, and recoverable errors.
AI agentsAgent Design PatternsFunction Calling
0 likes · 18 min read

The article examines the critical gap between read-only and write capabilities when AI agents access tools, showing how authorization boundaries blur, referencing NIST and Chinese standards, and proposing a three-layer framework — action, object, and result boundaries — to evaluate agent permissions and their security implications.
AI agentsChinese standardsNIST
0 likes · 8 min read

VideoGen-Agent, a Qwen3-VL-8B-based multimodal agent, learns via supervised fine-tuning and reinforcement learning to autonomously invoke retrieval, simulation, and verification tools for video generation, scoring 75.6 on VABench (19.1 points above base) and 86.1 with upgraded tools, while humans prefer its outputs 84.3% over Seedance 2.0.
Multimodal AgentsQwen3-VL-8BReinforcement Learning
0 likes · 20 min read

The article explores how AI agents are evolving from chat-based advisors into desktop agents that can read files, execute commands, and automate workflows, arguing that tool-use capability matters more than raw model intelligence for real productivity, while emphasizing the need for human oversight and task-design skills.
AI agentsAI safetyHuman-AI Collaboration
0 likes · 12 min read

Anthropic's new research reveals two agent paradigms: Nine Loops demonstrates a single agent completing a 96 CPU-week physics computation with only periodic check-ins, while ART orchestrates 949 agent sessions to autonomously discover a novel enzyme system, exposing critical insights on long-task reliability, multi-agent organization, tool-use pitfalls, and interpretability for attribution.
AI agentsARTAnthropic
0 likes · 12 min read

The author evaluates Seed-2.1-Pro 0915 against its predecessor using simulated tool failures, cropped financial PDFs, and a full analysis pipeline, finding both models honest when evidence is missing but revealing post-processing unit conversion errors, concluding that model execution requires system-level verification.
LLM EvaluationSeed-2.1-ProTool Use
0 likes · 15 min read


Amap TechSep 22, 2026 · Artificial Intelligence
Amap introduces DIANOIA, a multi-agent system that diagnoses and repairs low-confidence tool-call trajectories for navigation Live mode by generating diverse candidates, executing them in real tool environments, cross-reviewing failures, and synthesizing corrected sequences, boosting data quality for LLM training while reducing compute costs.
DIANOIAEMNLP 2026LLM agents
0 likes · 28 min read


IT XianyuSep 7, 2026 · Artificial Intelligence
This article analyzes OpenAI's GPT-6 Astra model, detailing its 1M-token context, tool-use capabilities, and pricing, while advising developers on suitable tasks like complex refactoring and multi-step automation, and emphasizing engineering discipline over raw specs to maximize cost-effectiveness.
AI pricingGPT-6 AstraLLM Evaluation
0 likes · 7 min read

This article dissects DeepSeek Harness's unified Session Log architecture where context management, memory compaction, and knowledge acquisition collaborate through layered context assembly, structure-preserving compaction, and tool-mediated retrieval — all traceable and replayable.
DeepSeek HarnessLSP IntegrationMemory Compaction
0 likes · 31 min read

The author demonstrates how an AI agent uses DeepSeek Harness's seven tools to dynamically create, register, run, stop, and version plugins in a sandboxed environment, with syntax validation, append-only versioning, and guided error messages, embodying a 'prevent errors, not malice' philosophy.
AI agentsDeepSeek HarnessTool Use
0 likes · 23 min read

OpenAI's GPT-6 Astra achieves 99.9% on the ARC-AGI-3 benchmark using its native Provider Adapter harness, demonstrating novel behaviors like inventing algebraic shorthand, surpassing human action efficiency, and writing its own tools, though the official standard harness yields 62.7%, raising questions about whether this constitutes AGI.
AGIAI benchmarksAI safety
0 likes · 17 min read


Geek LabsSep 5, 2026 · Artificial Intelligence
This article reviews an open-source book 'Deep Understanding of AI Agent' that structures AI Agent engineering around the formula Agent = LLM + Context + Tools, offering 10 chapters and 103 runnable Python experiments covering context engineering, memory, tool use, multi-agent collaboration, and model post-training.
AI agentLLMMCP Protocol
0 likes · 11 min read

This article argues that chat APIs alone are insufficient for AI agents; true agent systems require execution environments, tool loops, multi-tenant isolation, and layered architecture to move from demo to production-grade reliability across multiple entry points.
AI agentsLayered ArchitectureMulti-tenancy
0 likes · 22 min read

This article analyzes MemoHarness, a framework that evolves AI agents by optimizing six external harness dimensions—context assembly, tool interaction, generation control, task orchestration, memory management, and output processing—instead of model weights, demonstrating gains on terminal, coding, and finance tasks while noting limited experimental scale and selective cross-task transfer.
Agent HarnessAgent MemoryExternal System Evolution
0 likes · 22 min read

This article explains why AI systems produce different answers over time despite no apparent model updates, identifying five key variables—model configuration, knowledge retrieval, external tools, permissions, and human operations—and argues for lightweight 'explanation cards' to make answer changes traceable and governable.
AI governanceAI systemsNIST AI RMF
0 likes · 11 min read

The article explains that interviewers expect a detailed decomposition of an Agent's architecture, covering seven tightly linked capabilities—perception, planning, memory, tool use, action, reflection, and their closed‑loop cooperation—rather than a vague claim of merely calling a large model.
AI ArchitectureActionMemory
0 likes · 5 min read

The article explains why simply using a smarter model isn’t enough, showing that applying four fundamental AI‑agent design patterns—Reflection, Tool Use, Planning, and Multi‑Agent Collaboration—can raise GPT‑3.5’s HumanEval success from 48 % to over 95 %, and outlines how each pattern works, their trade‑offs, and practical implementation guidance.
AI agentReflectionTool Use
0 likes · 11 min read

OmniaBench, a new benchmark built from 90 primary and 354 secondary real‑world domains, evaluates 22 leading AI agents on 644 high‑difficulty tasks, revealing that even top models achieve less than 60% overall success, with detailed analysis of capability dimensions, efficiency, failure modes, and the impact of user simulators.
BenchmarkGeneral AI AgentsOmniaBench
0 likes · 26 min read

The article explains how AI has moved from chat interfaces to full‑workflow automation, outlines a formula for building valuable AI agents, reviews emerging Chinese AI‑agent products, and provides five practical tips and a step‑by‑step framework for turning everyday tasks into repeatable, testable Skills.
AIAgentsTool Use
0 likes · 19 min read

The article explains how AI agents differ from chatbots, outlines four core design patterns—Reflection, Tool Use, Planning, and Multi‑Agent Collaboration—draws on insights from DeepLearning.AI, Anthropic, Google Cloud, LangChain and Microsoft, and provides a step‑by‑step roadmap for evolving agents from personal assistants to enterprise‑wide intelligent systems.
AI agentAgentic WorkflowEnterprise AI
0 likes · 28 min read

This article provides a comprehensive, question‑and‑answer guide covering AI Agent fundamentals, core capabilities, workflow patterns, memory architectures, tool integration, planning algorithms, reflection mechanisms, security considerations, multi‑agent collaboration, deployment strategies, and practical engineering trade‑offs, offering concrete examples and best‑practice recommendations for each topic.
AI agentMemoryReflection
0 likes · 71 min read

The DIVE study shows that expanding the diversity of tool pools and task structures, rather than merely increasing the amount of homogeneous training data, dramatically improves LLM agents' ability to generalize to unseen tools, as demonstrated by a 12k‑vs‑48k experiment and reinforced by a four‑stage synthesis pipeline and RL fine‑tuning.
AI agentsDIVELLM training
0 likes · 14 min read

OpenAI’s July 2026 launch of ChatGPT Work, driven by GPT‑5.6, introduces a multi‑layer architecture that adds long‑context memory, native tool use and multimodal perception, enabling the model to operate real software, generate shareable sites, and compete with Anthropic and Google agents while exposing latency, security and cost challenges.
AI agentsChatGPT WorkGPT-5.6
0 likes · 11 min read


XikeJun 25, 2026 · Artificial Intelligence
The article explains that AI-powered code writing relies on an Agent Loop—Plan, Act, Observe, Reflect—rather than a single question‑answer exchange, detailing each phase, termination rules, common pitfalls, and practical guidelines for building reliable iterative agents.
AI codingTool Useagent loop
0 likes · 9 min read

The article explains that while an Agent’s core loop is only a few lines of code, the real engineering challenges lie in prompt design, context management, tool selection, and safety checks that together determine the loop’s effectiveness.
AnthropicLLMLoop Engineering
0 likes · 8 min read

The article defines AI Agent as a system centered on a large model that can invoke tools, receive feedback, and continuously accomplish tasks, and systematically distinguishes related terms such as Model, Scaffolding, Harness, Context Engineering, Policy, Tool, Skill, Sub‑agent, Environment, Rollout, Reward, and Trainer, using concrete examples to clarify each.
AI agentAgent TrainingHarness
0 likes · 10 min read

This article breaks down the full technology stack for production‑ready AI agents in 2026, covering model gateways, orchestration frameworks, tool‑use protocols, memory layers, state‑machine execution, sandboxing, observability, evaluation, and human‑in‑the‑loop safeguards, while highlighting concrete tools, risks, and best‑practice trade‑offs.
AI agentTool Usememory management
0 likes · 22 min read


SuanNiJun 6, 2026 · Artificial Intelligence
This article breaks down the core terminology of AI agents—Model, Scaffold, Harness, Context Engineering, Policy, Tool Use, Skills, Sub‑agents, and the training‑side concepts of RL Environment, Trainer, Rollout, and Reward—explaining their roles, differences, and how they combine to form functional agents.
AI agentHarnessPolicy
0 likes · 12 min read

This article provides a comprehensive overview of the "Code as Agent Harness" paradigm, detailing its three‑layer architecture, the roles of code in reasoning, acting, and environment modeling, the mechanisms that enable reliable long‑term execution, and how multi‑agent systems scale the harness through shared code and feedback loops.
Agent HarnessCode as AgentLLM
0 likes · 10 min read

The article introduces the ICML 2026 Theory of Agent (ToA), analyzes four common failure modes of modern agents, explains the internal‑vs‑external tool trade‑off through a knowledge‑boundary framework, and outlines how effort‑conservation and the β parameter guide self‑evolving agent design and future research.
AI agentsICML 2026Theory of Agent
0 likes · 24 min read

An AI Agent combines a large language model with a clear goal, callable tools, and a multi‑step reasoning loop, enabling perception, planning, and action that go beyond simple chat by decomposing tasks, using external APIs, iterating on errors, and managing memory, while acknowledging its limitations.
AI agentPerception-Planning-ActionTask Automation
0 likes · 7 min read

The article analyzes why traditional Retrieval‑Augmented Generation fails on multi‑hop, vague, or multi‑source queries and explains how Agentic RAG uses an LLM‑driven agent loop to make dynamic retrieval decisions, outlining its architecture, suitable scenarios, and limitations.
AI ReasoningAgentic RAGLLM agents
0 likes · 7 min read

The article analyzes MiniMax’s strategy of co‑evolving large language models with a Harness framework, contrasting product philosophies, detailing a live MaxHermes demo that creates and refines reusable Skills, and explaining how this dual evolution reshapes the competitive focus from single‑turn Q&A to sustained, self‑improving agent workflows.
AI agentsHermesMiniMax
0 likes · 14 min read

The article explains what an AI Agent is, how it differs from a large language model, outlines its three core abilities—autonomous planning, tool use, and memory—shows a step‑by‑step example, and discusses why agents have become popular and where they can be applied.
AI agentAI applicationsAutonomous Planning
0 likes · 12 min read


CodeTrendApr 21, 2026 · Artificial Intelligence
This article breaks down Microsoft’s open‑source AI‑Agent learning repository, explaining core concepts, five design patterns, production deployment considerations, and emerging protocols, while offering practical engineering guidance for building reliable multi‑agent systems from scratch.
AI agentsAgentic RAGMetacognition
0 likes · 10 min read

This article dissects the leaked Claude Code v2.1.88 source to reveal how the three core concepts—Rules, MCP, and Skills—are implemented, where they are injected in the Anthropic LLM API request, and when developers should prefer each mechanism for reliable, secure, and token‑efficient coding agent workflows.
Claude CodeLLM agentsMCP
0 likes · 25 min read

In this detailed lecture, Prof. Li Hongyi of National Taiwan University dissects the OpenClaw AI Agent, explaining its system prompts, tool usage, memory handling, sub‑agents, security risks like prompt injection, and practical safeguards for deploying autonomous agents on personal computers.
AI agentOpenClawPrompt Injection
0 likes · 35 min read

This article walks developers through the learn-claude-code project, teaching them how to construct a Claude‑style AI Agent Harness by covering twelve progressive lessons, core concepts such as agents, harnesses, sub‑agents, context compression, task management, and providing runnable Python examples and architectural diagrams.
AI agentAgent HarnessClaude Code
0 likes · 13 min read

This article explains how OpenClaw functions as an AI Agent framework that connects chat applications to large language models, manages multi‑turn dialogues, executes tool commands, handles memory and security, and demonstrates advanced features such as sub‑agents, cron jobs, and context compression.
AI agentOpenClawSecurity
0 likes · 19 min read

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.
AI agentMemoryTool Use
0 likes · 8 min read

This article explains why large language models need tool use, defines the concepts of Tool Use, Tool Call, and Function Calling, compares them, walks through a complete tool‑use workflow, and discusses architectural, safety, and design considerations for building reliable LLM agents.
LLMRuntimeTool Call
0 likes · 17 min read

This article explains why large language models alone can hallucinate, introduces the tool‑using agent architecture, and provides a step‑by‑step Python tutorial using LangChain, LangGraph, and Tavily to create, run, and evaluate a real‑time web‑search capable AI assistant.
LLMLangChainLangGraph
0 likes · 16 min read


Java OneMar 23, 2026 · Artificial Intelligence
This comprehensive guide walks you through the Claude Certified Architect exam structure, explains how Claude Code turns a language model into a full‑featured programming assistant, details installation on macOS, Linux and Windows, demonstrates tool‑use mechanics, context management, custom commands, and extending functionality with MCP servers such as Playwright.
AIClaudeMCP
0 likes · 27 min read

Recent studies reveal that in Agentic RL, jointly training reasoning and tool-use on shared parameters creates a persistent negative interaction, with gradients nearly orthogonal, limiting performance; a disentangled tuning approach (DART) using separate LoRA adapters isolates the two abilities and restores gains across benchmarks.
DartGradient InterferenceLoRA
0 likes · 12 min read

This article shows how to create an Easysearch intelligent assistant that lets users manage indexes, write data, search and aggregate documents using Chinese natural language, by combining the DeepSeek large‑language model with OpenAI‑compatible function calling (Tool Use) and a lightweight Node.js executor.
DeepSeekEasysearchLLM
0 likes · 12 min read

This article walks through converting the Easysearch command‑line assistant into a web‑based tool by adding an Express API layer, reusing shared logic, and building a lightweight HTML/CSS/JS front‑end, while preserving the original CLI capabilities.
APICLIDeepSeek
0 likes · 11 min read

This tutorial extends a minimal LLM Agent loop by introducing Tool Use (function calling) to give the agent actionable capabilities—searching the web, retrieving the current datetime, and performing mathematical calculations—while explaining the BaseTool architecture, registration process, system‑prompt adjustments, and practical execution examples.
AI agentBaseToolFunction Calling
0 likes · 15 min read

This article details the design, challenges, and performance gains of an AI‑driven rental recommendation system that replaces a multi‑agent architecture with a single LLM using dynamic tool‑use, introduces a two‑stage reinforcement‑learning pipeline, and achieves sub‑second latency and higher accuracy for complex rental scenarios.
AI recommendationReinforcement LearningTool Use
0 likes · 19 min read

Alibaba's new AgeMem framework turns long‑term and short‑term memory management for large language model agents into a learnable reinforcement‑learning task, replacing handcrafted rules with a three‑stage training process and achieving significant benchmark gains.
AgeMemBenchmarkGRPO
0 likes · 9 min read

This article explains the ReAct framework, which augments large language models with explicit reasoning, tool use, and observation loops to overcome hallucinations, improve transparency, and enable dynamic interaction with external environments across diverse tasks.
AI agentsReactTool Use
0 likes · 31 min read

The article breaks down how AI product managers can transform a raw base model into a market‑ready, high‑impact product by applying supervised fine‑tuning, tool‑use routing, RLHF alignment, and chain‑of‑thought reasoning, while highlighting trade‑offs, cost shifts, and evaluation metrics.
RLHFSFTTool Use
0 likes · 13 min read

This article explains the origins of AI Agent Skills, walks through the standard tool‑use loop, provides step‑by‑step code for defining and invoking Skills with the OpenAI API, compares Skills with the emerging Model Context Protocol (MCP), and offers practical guidance for developers and architects building AI‑enabled systems.
AI agent skillsFunction CallingMCP
0 likes · 11 min read

Claude Opus 4.5, Anthropic’s latest flagship LLM, dramatically upgrades reasoning, tool use, and multi‑step automation, targeting high‑intensity enterprise scenarios, offering stronger coding, longer context handling, and better cost‑effectiveness, while still requiring careful prompt engineering and budgeting for token usage.
Claude Opus 4.5Enterprise AILLM
0 likes · 7 min read

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.
AI agentMCPMemory System
0 likes · 35 min read

The article evaluates nine cutting‑edge AI models on 150 simulated workplace tasks, showing that even the strongest models complete fewer than 40% of tasks, and uses these results to propose a hierarchical framework of agentic capabilities ranging from tool use to common‑sense reasoning.
AI model evaluationReinforcement LearningTool Use
0 likes · 19 min read

VitaBench, a new open‑source benchmark from Meituan’s LongCat team, evaluates LLM‑driven agents across three realistic life‑service scenarios—food ordering, restaurant dining, and travel planning—using 66 tools and quantifying reasoning, tool, and interaction complexities, exposing a mere 30% success rate on complex cross‑scene tasks.
AIBenchmarkInteraction
0 likes · 14 min read

AgentFlow, a Stanford-led multi‑agent system built on a 7B model, outperforms massive models like GPT‑4o across ten benchmarks by leveraging modular agents, on‑policy learning, and a novel Flow‑GRPO training engine that solves sparse‑reward, long‑horizon challenges.
AgentFlowReinforcement LearningSmall Model Performance
0 likes · 12 min read

This article surveys recent Agentic RL research, detailing token templates, reward designs, training tricks, scaling laws, and multi‑stage frameworks that enable large language models to reason, search, and use tools autonomously.
LLM agentsMulti-Agent TrainingReinforcement Learning
0 likes · 28 min read

VitaBench is a newly released, highly realistic benchmark that evaluates large‑language‑model agents across three everyday scenarios—food ordering, restaurant dining, and travel planning—by quantifying reasoning, tool‑use, and interaction complexities, revealing a significant performance gap in current models.
AI-evaluationBenchmarkLLM agents
0 likes · 13 min read

This article analyzes the rStar2‑Agent paper, revealing how Agentic Reinforcement Learning, the GRPO‑RoC algorithm, a high‑throughput code‑execution service, and a three‑stage training recipe let a modest 14‑billion‑parameter model surpass much larger LLMs on challenging math benchmarks.
AI researchLLMModel Efficiency
0 likes · 18 min read

This article presents six practical AI Agent design patterns—chain, parallel, routing, coordinator‑executor, generator‑evaluator (reflection), and tool‑use—explaining their concepts, typical use cases, and workflow diagrams, and shows how they improve reliability, maintainability, and performance of LLM‑driven applications.
AI agentLLMReflection
0 likes · 20 min read

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.
AI agentActionMemory
0 likes · 7 min read

LongCat-Flash-Thinking, the latest open‑source model from Meituan, introduces domain‑parallel RL training, a high‑throughput DORA infra, and a dual‑path inference framework that together achieve state‑of‑the‑art performance on logical, mathematical, coding, and agentic tasks while maintaining top‑tier speed.
BenchmarkLongCatRL training
0 likes · 10 min read

Meituan’s LongCat team unveiled LongCat-Flash-Thinking, an open‑source large language model that combines deep logical reasoning with tool‑calling capabilities, achieving state‑of‑the‑art performance across logic, mathematics, code, and agentic tasks, and introducing novel training frameworks such as domain‑parallel RL and DORA.
AIBenchmarkTool Use
0 likes · 7 min read

This article explains why the Model Context Protocol (MCP) is needed for LLMs, describes its client‑server architecture, data and transport layers, and provides step‑by‑step Python examples for creating both an MCP server and a client using FastMCP and low‑level APIs.
FastMCPLLMMCP
0 likes · 18 min read

Kimi K2, an open‑source trillion‑parameter AI model released by Moonshot AI, offers Base and Instruct variants, achieves leading scores on benchmarks such as SWE‑bench, LiveCodeBench and AceBench, and introduces a novel post‑training autonomous‑exploration stage with MuonClip optimization to enable robust tool use and reinforcement‑learning‑driven self‑improvement.
Kimi K2Reinforcement LearningTool Use
0 likes · 8 min read

AI Agents, autonomous intelligent programs that perceive, reason, and act, are reshaping industries from healthcare to autonomous driving; this article explains their core components, differences from large language models, planning techniques, memory mechanisms, tool use, real‑world applications, current challenges, and future directions.
AI agentApplicationsMemory
0 likes · 35 min read

This comprehensive guide walks you through the fundamentals of Retrieval‑Augmented Generation (RAG) and AI agents, explains their inner workings, shares optimization tricks, provides ready‑to‑run code snippets, and demonstrates how to evaluate performance with metrics such as recall, faithfulness, and answer relevance.
AI agentsLLMRAG
0 likes · 36 min read

This article explains the importance of planning for multi‑tool AI agents, compares OpenAI and Anthropic approaches, presents experimental results, and provides practical guidance on tool design, prompt configuration, model selection, and parallel versus serial tool calls to improve efficiency and effectiveness.
AI agentsAnthropicOpenAI
0 likes · 16 min read

This article demystifies AI agents and agentic workflows, explaining their core components—LLMs, tools, and memory—while detailing planning, tool‑use, and reflection patterns, comparing agentic, non‑agentic, and traditional workflows, and exploring real‑world applications, advantages, and limitations.
AI agentsAgentic workflowsLLM
0 likes · 21 min read

AI agents are rapidly evolving toward a 2025 breakthrough in perception, autonomous planning, tool use and memory, driven by multimodal models, neural‑symbolic reasoning and embodied intelligence, with $27 billion investment forecasts, exemplified by general‑purpose agents like Manus and emerging applications in code generation, research, healthcare, and risk analysis.
AI agentAutonomous PlanningMemory
0 likes · 12 min read

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.
AI agentsBenchmarkMemory
0 likes · 67 min read

The article explains how large language models extend their capabilities by using tool calls—detailing the need for external APIs, the three‑stage workflow, request/response formats, autonomous routing, parameter generation, error handling, and the relationship between Function Calling and Tool Use.
AI Autonomous DecisionFunction CallingJSON:API
0 likes · 12 min read

This article breaks down the key endpoint features of large language models—such as quantization, max token limits, streaming cancellation, tool support, and reasoning ability—explaining what each term means, why it matters, and how to choose models wisely for different applications.
AI model evaluationEndpoint FeaturesLLM
0 likes · 11 min read

This article provides a comprehensive overview of AI Agents, tracing their evolution from traditional chatbots to LLM‑driven agents, explaining core components such as perception, reasoning, action, knowledge bases, learning and communication interfaces, and discussing practical use cases, interaction cycles, and future prospects.
AI agentsRetrieval-Augmented GenerationTool Use
0 likes · 15 min read

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.
ChatDevReflectionTool Use
0 likes · 9 min read


DevOpsDec 12, 2024 · Artificial Intelligence
Andrew Ng highlights that large language models are shifting from optimizing simple question‑answering for consumers to supporting complex agentic workflows, including tool usage, computer interaction, and multi‑agent collaboration, signaling a major evolution in AI capabilities.
AI TrendsAI agentsAgentic AI
0 likes · 8 min read

This article surveys the rapid rise of AI agents powered by large language models, explaining their core perception‑planning‑action loop, memory architectures, tool‑use mechanisms, self‑reflection techniques, and real‑world case studies while highlighting current challenges and future prospects for autonomous intelligent systems.
AI agentLLMMemory
0 likes · 29 min read

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.
AI agentsFrameworksFunction Calling
0 likes · 20 min read

The article explains Andrew Ng’s four AI agent design patterns—Reflection, Tool Use, Planning, and Multi‑agent Collaboration—illustrates each with concrete Coze workflows and real‑world examples such as automotive research briefs, milk‑tea industry reports, and high‑quality travel planning.
AI agentsCozeReflection
0 likes · 7 min read


ArchitectNov 8, 2023 · Artificial Intelligence
The article dissects the rise of AI agents—from OpenAI's Assistants API and multimodal perception‑brain‑action pipelines to retrieval‑augmented generation, tool‑use strategies, single‑ and multi‑agent deployments, and emerging frameworks like AutoGen—while highlighting concrete examples, benchmark results, and current limitations.
AI agentsAssistants APIEmbodied AI
0 likes · 38 min read

The survey shows that once language models exceed roughly ten billion parameters they spontaneously acquire two complementary abilities—step‑by‑step reasoning, often elicited by chain‑of‑thought prompts or scratch‑pad training, and the capacity to invoke external tools such as search engines, calculators, or robots—enabling them to retrieve up‑to‑date information, perform complex computations, and act in the world, thereby advancing toward general artificial intelligence.
AIRetrieval AugmentationTool Use
0 likes · 20 min read
