让大模型学会自主设定目标、长期规划，像人一样思考决策。
Rethinking Agentic Reinforcement Learning In Large Language Models
- 将大模型与强化学习结合，实现自主目标设定和动态策略调整。
- 引入元推理、自我反思等认知能力，支持复杂环境下的持续学习。
- 适合对智能体自主性、泛化能力感兴趣的科研与工程人员。
强化学习（RL）传统上聚焦于训练专用智能体在特定环境中优化预定义奖励函数。然而，随着强大大语言模型（LLMs）的出现以及任务日益复杂且开放，强化学习正朝着以智能体为核心的范式转变。这一新兴框架超越了传统方法，强调构建具备自主目标设定、长期规划、动态策略适应及不确定环境下交互推理能力的智能体。与依赖静态目标和周期性交互的传统方法不同，基于大模型的智能体强化学习将元推理、自我反思和多步决策等类认知能力直接融入学习过程。本文深入剖析该趋势的概念基础、方法创新与有效设计，并识别关键挑战，展望未来构建基于大模型的智能体强化学习的可行方向。
原文摘要 · Abstract (English)
Reinforcement Learning (RL) has traditionally focused on training specialized agents to optimize predefined reward functions within narrowly defined environments. However, the advent of powerful Large Language Models (LLMs) and increasingly complex, open-ended tasks has catalyzed a paradigm shift towards agentic paradigms within RL. This emerging framework extends beyond traditional RL by emphasizing the development of autonomous agents capable of goal-setting, long-term planning, dynamic strategy adaptation, and interactive reasoning in uncertain, real-world environments. Unlike conventional approaches that rely heavily on static objectives and episodic interactions, LLM-based Agentic RL incorporates cognitive-like capabilities such as meta-reasoning, self-reflection, and multi-step decision-making directly into the learning loop. In this paper, we provide a deep insight for looking the conceptual foundations, methodological innovations, and effective designs underlying this trend. Furthermore, we identify critical challenges and outline promising future directions for building LLM-based Agentic RL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。