Agentic AI — Weblinks

A

Building effective agents (Anthropic) Art… 5 terms

A

How we built our multi-agent research system (Anthropic) Art… 5 terms

A

Building effective AI agents — Anthropic Art… 4 terms

A

Effective context engineering for AI agents — Anthropic Engineering (compaction) Art… 4 terms

D

Multi-agent — LangChain docs Docs 4 terms

P

Define tools — Claude Docs Docs 3 terms

D

Memory overview — LangChain docs (semantic, episodic, procedural) Docs 3 terms

O

Tracing — OpenAI Agents SDK Art… 3 terms

A

Writing effective tools for agents — why not to wrap every API endpoint (Anthropic Engineering) Art… 3 terms

D

AGENTSEC04-BP02 Human-in-the-loop for critical decisions - AWS Well-Architected Agentic AI Lens (risk-tiered approval, timeouts, audit log) Docs 2 terms

M

autogen_agentchat.conditions — MaxMessageTermination and other caps (AutoGen reference) Art… 2 terms

A

Chapter 2: Intelligent Agents (PEAS task environments, environment properties) — AIMA notes Docs 2 terms

P

Context windows — Claude Docs Docs 2 terms

A

CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing Pap… 2 terms

A

Generative Agents: Interactive Simulacra of Human Behavior Pap… 2 terms

P

Handle tool calls: matching results to tool_use ids — Claude Docs Docs 2 terms

D

Human-in-the-loop - LangGraph docs (checkpointed pause, present the proposed tool call, resume on approve/edit/reject) Docs 2 terms

A

Introducing advanced tool use on the Claude Developer Platform (Anthropic Engineering) Art… 2 terms

A

Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena Pap… 2 terms

D

LangSmith Observability Docs 2 terms

A

Least-to-Most Prompting Enables Complex Reasoning in Large Language Models Pap… 2 terms

D

Long-term memory | LangChain docs Docs 2 terms

O

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments (official project page) Art… 2 terms

A

ReAct: Synergizing Reasoning and Acting in Language Models Pap… 2 terms

A

Reflexion: Language Agents with Verbal Reinforcement Learning Pap… 2 terms

D

Short-term memory | LangChain docs Docs 2 terms

A

SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering Pap… 2 terms

D

Use time-travel — LangGraph (replay and fork from a checkpoint) Docs 2 terms

H

What are agents? An introduction to agentic systems — smolagents docs Docs 2 terms

D

Workflows and agents — LangGraph documentation Docs 2 terms

A

A Survey on Code Generation with LLM-based Agents Pap… 1 term

A

A Survey on Large Language Models for Automated Planning Pap… 1 term

A

A2A Specification 8 - Agent Discovery: The Agent Card Art… 1 term

H

Actions: Enabling the Agent to Engage with Its Environment — Hugging Face Agents Course Docs 1 term

A

ADaPT: As-Needed Decomposition and Planning with Language Models Pap… 1 term

D

ADK overview — Google Cloud agent platform documentation Docs 1 term

A

Agent Development Kit (ADK) — official documentation Art… 1 term

A

Agent Discovery - A2A Protocol (/.well-known/agent-card.json) Art… 1 term

D

Agent Evals — LangChain/LangSmith docs: trajectory match and LLM-as-judge trajectory evaluators Docs 1 term

O

Agent orchestration - OpenAI Agents SDK Art… 1 term

C

Agent SDK overview - build production AI agents with Claude Code as a library Docs 1 term

A

Agent2Agent (A2A) Protocol Specification v1.0.0 Art… 1 term

A

AgentBench: Evaluating LLMs as Agents (ICLR 2024) Pap… 1 term

A

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents Pap… 1 term

D

AGENTREL02-BP05 Establish tiered human oversight and approval workflows - AWS Well-Architected Agentic AI Lens Docs 1 term

D

Agents - CrewAI Docs (role, goal, backstory, tools) Docs 1 term

D

Agents - LlamaIndex Framework Component Guides Art… 1 term

D

Agents — LangChain docs Docs 1 term

D

AGENTSEC03-BP03 Implement least privilege with dynamic boundaries - AWS Well-Architected Agentic AI Lens Docs 1 term

A

AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society (arXiv:2502.08691) Pap… 1 term

A

AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities Pap… 1 term

A

AI Agents That Matter (Kapoor et al., Princeton) — accuracy-only agent benchmarking and cost Pap… 1 term

A

Aider Documentation Docs 1 term

G

Aider-AI/aider — AI pair programming in your terminal Code 1 term

A

An Illusion of Progress? Assessing the Current State of Web Agents (Online-Mind2Web) Pap… 1 term

D

Assistants migration guide - OpenAI (assistants/threads/runs to Responses API) Docs 1 term

M

AutoGen - official documentation (AgentChat, Core, Extensions, Studio) Art… 1 term

A

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation (arXiv:2308.08155) Pap… 1 term

G

AutoGPT Classic — the original autonomous GPT-4 agent Code 1 term

E

AutoGPT — Wikipedia Ref… 1 term

Y

Birth of BabyAGI — Yohei Nakajima Art… 1 term

E

Blackboard (design pattern) - Wikipedia Ref… 1 term

A

BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents Pap… 1 term

G

browser-use — open-source Python library for AI browser agents Code 1 term

M

Build an MCP client - official MCP tutorial Docs 1 term

M

Build an MCP server - official MCP tutorial Docs 1 term

A

CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society Pap… 1 term

A

Chain-of-Thought Prompting Elicits Reasoning in Large Language Models Pap… 1 term

P

Chain-of-Thought Prompting — Prompt Engineering Guide Art… 1 term

A

ChatDev: Communicative Agents for Software Development Pap… 1 term

D

Checkpointers — LangGraph (checkpoints, super-steps, durability modes) Docs 1 term

A

Chronicle: Cut-Point Replay for Regression Testing of LLM Agents Pap… 1 term

A

Code Execution - Kubernetes Agent Sandbox (untrusted agent code in isolated pods, gVisor/Kata) Docs 1 term

P

Code execution tool: run Python and Bash in a sandboxed container — Claude Docs Docs 1 term

A

Code execution with MCP: composing tool calls in code (Anthropic Engineering) Art… 1 term

D

Code Interpreter — OpenAI API Guides Docs 1 term

L

Codex Cloud - run coding tasks in the cloud (ChatGPT Learn docs) Docs 1 term

A

Cognitive Architectures for Language Agents (CoALA) — Sumers, Yao, Narasimhan, Griffiths Pap… 1 term

P

Compaction overview — Claude Docs Docs 1 term

P

Computer use tool — Claude Docs Docs 1 term

G

computer-use-demo — Anthropic claude-quickstarts reference implementation Code 1 term

C

Configure permissions - Claude Code docs (fine-grained allow/ask/deny tool rules and managed policy) Docs 1 term

L

Context Engineering (scratchpads, write/select/compress/isolate) | LangChain Blog Art… 1 term

L

Context Engineering — LangChain blog (write, select, compress, isolate) Art… 1 term

A

Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation Pap… 1 term

D

Crews - CrewAI Docs (sequential and hierarchical processes, manager agent) Docs 1 term

A

Data Interpreter: An LLM Agent For Data Science Pap… 1 term

A

Deep Research Agents: A Systematic Examination And Roadmap Pap… 1 term

D

Dialogflow CX handoff - Google Cloud Agent Assist (human-escalation event and live agent handoff) Docs 1 term

A

Do As I Can, Not As I Say: Grounding Language in Robotic Affordances (SayCan) Pap… 1 term

O

Doom-Loop Detection — OpenRouter Agent SDK (observe, steer, escalate, block, stop) Docs 1 term

D

Durable AI — Temporal (durable execution: a workflow resumes automatically after a crash) Docs 1 term

P

Durable Execution — Pydantic AI Docs 1 term

A

Effective harnesses for long-running agents — Anthropic Engineering Art… 1 term

T

Escalate to a human agent - Twilio docs (handoff triggers and HandoffPayload carrying conversation context) Docs 1 term

C

Evaluate Gen AI agents — trajectory metrics (exact/in-order/any-order match, precision, recall) Docs 1 term

A

Exploring Advanced LLM Multi-Agent Systems Based on Blackboard Architecture Pap… 1 term

A

Exponential Backoff And Jitter — AWS Architecture Blog (full, equal, decorrelated jitter) Art… 1 term

I

Fin AI Agent explained - Intercom Help Art… 1 term

A

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem Pap… 1 term

A

Function calling with the Gemini API — Google AI for Developers Docs 1 term

D

Function calling — OpenAI API docs Docs 1 term

H

GAIA Leaderboard — Hugging Face Space (gaia-benchmark) Docs 1 term

A

GAIA: a benchmark for General AI Assistants Pap… 1 term

S

Get personalization in Gemini Apps - Gemini Apps Help Art… 1 term

G

GitHub - anthropics/claude-agent-sdk-python: Python SDK for Claude Agent Code 1 term

G

GitHub - langchain-ai/langchain: the agent engineering platform Code 1 term

G

GitHub - langchain-ai/langgraph: low-level orchestration framework for stateful agents Code 1 term

G

GitHub - openai/openai-agents-python: a lightweight, powerful framework for multi-agent workflows Code 1 term

G

GitHub - openai/swarm: educational framework exploring ergonomic, lightweight multi-agent orchestration Code 1 term

D

Graph API overview - LangGraph Docs Docs 1 term

D

GRAPH_RECURSION_LIMIT — LangGraph recursion_limit step cap Docs 1 term

O

Guardrails - OpenAI Agents SDK (input and output guardrails with tripwires) Art… 1 term

D

Guardrails and human review - OpenAI Agents docs (per-tool needsApproval, run pauses until approve or reject) Docs 1 term

A

GUI Agents: A Survey Pap… 1 term

O

Handoffs - OpenAI Agents SDK Art… 1 term

D

How to evaluate your agent with trajectory evaluations Docs 1 term

A

How to Measure Task Success Rate in AI Agents Art… 1 term

P

How tool use works (the agentic loop) — Claude Docs Docs 1 term

D

Human-in-the-loop patterns - Cloudflare Agents (requiresApproval on a connector method, approve()/reject()) Art… 1 term

A

Improving Factuality and Reasoning in Language Models through Multiagent Debate Pap… 1 term

A

Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback Pap… 1 term

A

InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks Pap… 1 term

O

Inside the LLM Call: GenAI Observability with OpenTelemetry (token usage, operation duration) Art… 1 term

D

Interrupts — LangGraph (pause and resume with Command(resume=…)) Docs 1 term

D

Introducing Devin — Devin documentation Docs 1 term

C

Introducing Devin, the first AI software engineer (Cognition) Art… 1 term

L

Introduction to Semantic Kernel - Microsoft Learn Art… 1 term

D

Introduction — Chroma documentation Docs 1 term

D

LangChain overview - LangChain Docs Docs 1 term

G

langchain-ai/langgraph-supervisor-py - hierarchical multi-agent systems with LangGraph Code 1 term

D

LangSmith Evaluation (datasets, evaluators, offline and online) Docs 1 term

A

Large Language Models Cannot Self-Correct Reasoning Yet Pap… 1 term

L

LLM Powered Autonomous Agents (Lil'Log) Art… 1 term

L

LLM Powered Autonomous Agents — Task Decomposition (Lil'Log) Art… 1 term

G

LLM01:2025 Prompt Injection - OWASP Gen AI Security Project Art… 1 term

C

Manage costs effectively — Claude Code (spend limits, model choice, caching, context) Docs 1 term

I

Manage Fin AI Agent's escalation guidance and rules - Intercom Help Art… 1 term

P

MCP connector: remote servers, OAuth tokens and per-tool configuration — Claude Docs Docs 1 term

M

MCP specification - Authorization for HTTP-based transports Art… 1 term

M

MCP specification - Prompts (prompts/list, prompts/get, arguments) Art… 1 term

M

MCP specification - Resources (URIs, MIME types, subscriptions) Art… 1 term

M

MCP specification - Tools (tools/list, inputSchema, list_changed) Art… 1 term

M

MCP specification - Transports (stdio, Streamable HTTP) Art… 1 term

A

MemGPT: Towards LLMs as Operating Systems Pap… 1 term

L

Memory for agents — LangChain blog (procedural memory and the system prompt) Art… 1 term

O

Mind2Web project page (OSU NLP) — 2,350 tasks, 137 websites, cross-task/website/domain settings Art… 1 term

A

Mind2Web: Towards a Generalist Agent for the Web Pap… 1 term

G

noahshinn/reflexion — code, demos and logs for the Reflexion paper Code 1 term

G

NVIDIA NeMo Guardrails - programmable input, output, dialog, retrieval and execution rails for LLM apps Code 1 term

H

Observe: Integrating Feedback to Reflect and Adapt — Hugging Face Agents Course Docs 1 term

O

OpenAI Agents SDK - official Python documentation Art… 1 term

D

Orchestrating Agents: Routines and Handoffs - OpenAI Cookbook Art… 1 term

A

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments (arXiv paper, NeurIPS 2024) Pap… 1 term

P

Output — Pydantic AI (Pydantic-validated structured output, ModelRetry) Docs 1 term

P

Parallel tool use — Claude Docs Docs 1 term

D

Persistence — LangGraph (checkpointers, threads, fault tolerance) Docs 1 term

A

Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security Pap… 1 term

G

pgvector — vector similarity search for Postgres Code 1 term

L

Plan-and-Execute Agents (LangChain blog) Art… 1 term

A

Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models Pap… 1 term

P

Programmatic tool calling: multi-tool workflows from code — Claude Docs Docs 1 term

P

Prompt caching — Claude API (cache reads at a fraction of input price) Docs 1 term

P

Pydantic AI — official documentation overview Docs 1 term

R

ReAct: Synergizing Reasoning and Acting in Language Models (Google Research blog) Art… 1 term

A

Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models — Wang et al. Pap… 1 term

P

Reflexion | Prompt Engineering Guide Art… 1 term

A

REMem: Reasoning with Episodic Memory in Language Agent Pap… 1 term

R

RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control Art… 1 term

C

Run Claude Code programmatically (non-interactive mode, unattended runs) Docs 1 term

C

Sandboxing - Claude Code docs (OS-level filesystem and network isolation for agent shell commands) Docs 1 term

H

Secure code execution — smolagents (LocalPythonExecutor and remote sandboxes) Docs 1 term

A

Self-Consistency Improves Chain of Thought Reasoning in Language Models Pap… 1 term

A

Self-Refine: Iterative Refinement with Self-Feedback Pap… 1 term

L

Semantic Kernel Agent Framework - Microsoft Learn Art… 1 term

L

Semantic Search for LangGraph Memory — LangChain blog Art… 1 term

A

Separating Capability from Permission: A Governance Framework for Agentic AI Autonomy Levels Pap… 1 term

A

Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs Pap… 1 term

G

sierra-research/tau-bench — code, retail and airline domains, Pass^k leaderboard Code 1 term

H

smolagents — Hugging Face documentation (CodeAgent, ToolCallingAgent) Docs 1 term

M

Specification — Model Context Protocol (revision 2026-07-28) Art… 1 term

D

Structured model outputs — OpenAI API Guides Docs 1 term

P

Structured outputs — Claude Docs Docs 1 term

G

SWE-agent — official repository (Princeton/Stanford) Code 1 term

S

SWE-bench Leaderboards — Verified, Lite, Full, Multimodal, Multilingual Art… 1 term

A

SWE-bench: Can Language Models Resolve Real-World GitHub Issues? Pap… 1 term

A

Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems Pap… 1 term

P

Task budgets — Claude API (token budget for a full agentic loop, countdown, exhaustion behaviour) Docs 1 term

A

tau-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains Pap… 1 term

M

Termination — AutoGen (built-in termination conditions and how to combine them) Art… 1 term

T

The definitive guide to Durable Execution Art… 1 term

A

The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents Pap… 1 term

S

The lethal trifecta for AI agents: private data, untrusted content, and external communication Art… 1 term

G

THUDM/AgentBench — benchmark code, 8 interactive environments (OS, DB, KG, web, games) Code 1 term

B

Timeouts, retries, and backoff with jitter — Amazon Builders' Library Art… 1 term

P

Tool search tool: on-demand tool loading with defer_loading — Claude Docs Docs 1 term

P

Tool use with Claude — Claude Docs Docs 1 term

D

Tool-loop detection — warning then blocking on repeated identical tool calls Docs 1 term

D

Tools (FunctionTool, QueryEngineTool, Tool Specs) - LlamaIndex Art… 1 term

M

Tools — MCP specification: protocol errors vs tool execution errors (isError) Art… 1 term

M

Tools — Model Context Protocol specification (inputSchema, outputSchema) Art… 1 term

O

Traces — OpenTelemetry (spans, parent/child nesting, timing, status) Docs 1 term

P

Tree of Thoughts (ToT) | Prompt Engineering Guide Art… 1 term

A

Tree of Thoughts: Deliberate Problem Solving with Large Language Models Pap… 1 term

D

Turns overview - LiveKit Agents docs (turn detection & interruptions) Docs 1 term

H

Understanding AI Agents through the Thought-Action-Observation Cycle — Hugging Face Agents Course Docs 1 term

M

Understanding MCP clients (elicitation, roots, sampling) Docs 1 term

M

Understanding MCP servers (tools, resources, prompts) Docs 1 term

M

Understanding MCP servers - Prompts Docs 1 term

M

Understanding MCP servers - Resources Docs 1 term

M

Understanding MCP servers: tools, resources and prompts — Model Context Protocol Docs 1 term

H

Using LLM-as-a-judge for an automated and versatile evaluation — Hugging Face Cookbook Docs 1 term

D

Voice agents - OpenAI API guide Docs 1 term

G

web-arena-x/webarena — self-hostable web environment and 812 evaluation tasks Code 1 term

A

WebArena: A Realistic Web Environment for Building Autonomous Agents Pap… 1 term

A

What is A2A? - A2A Protocol (incl. how it differs from MCP) Art… 1 term

H

What is an Agent? — Hugging Face Agents Course, Unit 1 Docs 1 term

N

What should an AI agent audit trail include? (NHI Mgmt Group) Art… 1 term

G

yoheinakajima/babyagi_archive — the original task-driven autonomous agent Code 1 term