500篇论文的智能体RL地图
一篇综述论文系统梳理了面向大语言模型的智能体强化学习方法，覆盖 500 余篇相关工作。论文将现有研究分为能力与应用两大部分：能力部分涵盖记忆、规划、工具使用、推理、多模态感知和自我改进；应用部分展示这些方法在复杂任务中的落地。核心观点是传统 LLM 训练只奖励单次回答，而真实任务需要多步决策与延迟反馈，强化学习恰好能解决这一时序学习问题。
Nice survey paper mapping agentic reinforcement le…
Nice survey paper mapping agentic reinforcement learning for LLMs, showing how models learn by acting across time.
Covers 500+ works and groups them into a 2-part map of capabilities and applications.
The problem is that common LLM training rewards a single answer once, then stops learning.
Real tasks need many steps, partial information, and choices that affect what happens later.
The survey formalizes that setup as an agent that sees a bit, chooses an action, and gets feedback.
That perspective uses memory to track context, planning to pick sequences, and tools to affect the world.
It also includes reasoning for constraint handling, perception for multimodal inputs, and self-improvement to refine policies.
Reinforcement learning links all of this, because rewards arrive after sequences, so the policy learns what to try next.
----
Paper – arxiv. org/abs/2509.02547
Paper Title: "The Landscape of Agentic Reinforcement Learning for LLMs: A Survey"