The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

Authors: Guibin Zhang, Hejia Geng, Xiaohang Yu, Zhenfei Yin, Zaibin Zhang, Zelin Tan, Heng Zhou, Zhongzhi Li, Xiangyuan Xue, Yijiang Li, Yifan Zhou, Yang Chen, Chen Zhang, Yutao Fan, Zihu Wang, Songtao Huang, Francisco Piedrahita-Velez, Yue Liao, Hongru Wang, Mengyue Yang, Heng Ji, Jun Wang, Shuicheng Yan, Philip Torr, and Lei Bai.

This survey formalizes Agentic Reinforcement Learning as sequential decision-making in dynamic environments. It organizes the field around core agent capabilities and application domains, while cataloging representative environments, benchmarks, and frameworks.

Links: TMLR / OpenReview · arXiv