The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

TMLR Paper6337 Authors

Abstract: The emergence of agentic reinforcement learning (Agentic RL) marks a paradigm shift from conventional reinforcement learning applied to large language models (LLM RL), reframing LLMs from passive sequence generators into autonomous, decision-making agents embedded in complex, dynamic worlds. This survey formalizes this conceptual shift by contrasting the degenerate single-step Markov Decision Processes (MDPs) of LLM-RL with the partially observable, temporally extended partially observable Markov decision process (POMDP) that define Agentic RL. Building on this foundation, we propose a comprehensive twofold taxonomy: one organized around core agentic capabilities, including planning, tool use, memory, reasoning, self-improvement, and perception, and the other around their applications across diverse task domains. Central to our thesis is that reinforcement learning serves as the critical mechanism for transforming these capabilities from static, heuristic modules into adaptive, robust agentic behavior. To support and accelerate future research, we consolidate the landscape of open-source environments, benchmarks, and frameworks into a practical compendium. By synthesizing over five hundred recent works, this survey charts the contours of this rapidly evolving field and highlights the opportunities and challenges that will shape the development of scalable, general-purpose AI agents.

Submission Type: Long submission (more than 12 pages of main content)

Changes Since Last Submission: This article has not been rejected by TMLR. This is a resubmission because an author was accidentally overlooked. It has been approved by the editor via email.

Assigned Action Editor: ~Blake_Aaron_Richards1

Submission Number: 6337