Lately, I've been diving into agentic RL for LLMs—a fascinating topic that sits neatly at the intersection of many of my technical interests. In this post, I share high-level, flashcard-style of key ideas from one of the better survey papers I've come across—The Landscape of Agentic Reinforcement Learning for LLMs: A Survey—including techniques for LLM planning, tool use, memory management, self-improvement, and reasoning. If these resonate, please let me know in the comments and I'll happily share more.