Gen-Verse/Open-AgentRL

项目介绍

RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System

An overview of our research on RLAnything.

In this work, we propose RLAnything, a reinforcement learning framework that dynamically optimizes each component through closed-loop optimization, amplifying learning signals and strengthening the overall system:

An overview of our research on agentic RL.

In this work, we systematically investigate three dimensions of agentic RL: data, algorithms, and reasoning modes. Our findings reveal:

We also contribute high-quality SFT and RL datasets, demonstrating that simple recipes enable even 4B models to outperform 32B models on challenging benchmarks including…

摘自 github.com/Gen-Verse/Open-AgentRL