LLM Agents

What Is an Agent, Really?
Introduction to LLM Agents
Methodologies and Core Patterns
Candidate Generation and Selection
Critique, Revision, and Acceptance
Planning and Execution
Runtime State, Progress, and Termination
Memory and Selective Recall
Trajectory Search
The Memory Contamination Problem
References and Supporting Papers
Advanced Agents From First Principles 06: Does One Agent Plan, Execute and Judge Its Own Work? Build a Planner-Executor-Critic Architecture
Agents From First Principles 08: AI Agent Picks the First Solution? Add Search Instead of One-Shot Generation
Agents From First Principles 07: AI Agent Forgets Previous Work? Add Working, Semantic and Episodic Memory
Agents From First Principles 05: AI Agent Gets Stuck in a Loop? Add State, Feedback and Stopping Conditions
Agents From First Principles 04: AI Agent Fails on Multi-Step Tasks? Separate Planning From Execution
Agents From First Principles 03: AI Agent Keeps Making the Same Mistake? Add a Critique-and-Revision Loop
Agents From First Principles 02: AI Agent Gives Inconsistent Answers? Generate Multiple Candidates and Rank Them
Agents From First Principles 00: What Is an Agent, Really?
Intelligence Through Execution: The Executable Cognitive Kernel