SPO++: Stream-Aligned Policy Optimization for Asynchronous Agentic RL
Group-relative reinforcement learning waits for sibling rollouts of the same prompt, which is costly for long and variable tool-use trajectories. Single-stream Policy Optimization (SPO) removes this dependency with a persistent prompt-level value estimate, but its recipe whitens one advantage per trajectory before optimizing a token-mean actor loss. We show that trajectory centering generally…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
