LLM-RL-learn - a PanEa Collection

PanEa 's Collections

thinking-mechanisms

long-horizon-agent

generative-engine

deep-research-eval

deep-research-data

agentic-data-synthesis

MLLM

LLM-RL-learn

updated Sep 4

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

Paper • 2509.02547 • Published Sep 2 • 224