# StaleFlow: Staleness-Aware Data Management for Mitigating Data Skewness in Fully Disaggregated RL Post-Training

arXiv: https://arxiv.org/abs/2601.12784 · HTML: https://mlsanity.com/paper/2601.12784/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jan 2026.

## Built on by (most cited first, 11 of 11)

- [ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments](https://mlsanity.com/paper/2609.19134/) (2026)
- [Harnessing Routing Foresight for Micro-step-level MoE load balancing in RL Post-training](https://mlsanity.com/paper/2606.11867/) (2026)
- [AREAL-DTA: Dynamic Tree Attention for Efficient Reinforcement Learning of Large Language Models](https://mlsanity.com/paper/2602.00482/) (2026)
- [MARLaaS: Multi-Tenant Asynchronous Reinforcement Learning as a Service](https://mlsanity.com/paper/2605.08527/) (2026)
- [Deconstructing Off-Policy Ratios: Entropy-Normalized Trust Regions for Asynchronous Reinforcement Learning](https://mlsanity.com/paper/2607.22186/) (2026)
- [Performance Foundations of Parallel & Distributed Reasoning Language Models](https://mlsanity.com/paper/2608.27046/) (2026)
- [Rollout Efficiency in Reinforcement Learning for Reasoning Large Language Models: A Taxonomy and Future Directions](https://mlsanity.com/paper/2609.25463/) (2026)
- [QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents](https://mlsanity.com/paper/2609.33848/) (2026)
- [Cool the Sampler, Not the Learner: Sampling Temperature Moves the Staleness Cliff of Importance-Corrected GRPO](https://mlsanity.com/paper/2609.36953/) (2026)
- [KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization](https://mlsanity.com/paper/2610.14448/) (2026)
- [Efficient Resource-Shiftable RL Post-training with Generative Rewards](https://mlsanity.com/paper/2610.16866/) (2026)

## Abstract (arXiv)

Reinforcement learning (RL) post-training has become pivotal for enhancing the capabilities of modern large models. A recent trend is to develop RL systems with a fully disaggregated architecture, which decouples the three RL phases (rollout, reward, and training) onto separate resources and executes them asynchronously. However, two critical data-level concerns arise: (1) asynchronous execution leads to data staleness in trajectories (the data generated by rollout) as the model parameters used in rollout may not be up to date, which impairs RL convergence; and (2) the length variation of trajectories introduces severe data skewness, leading to workload imbalance and degraded system performance. Existing systems fail to address these two concerns in a unified manner. Techniques that tightly control data staleness often constrain effective data skewness mitigation, while aggressive data skewness mitigation tends to exacerbate data staleness. As a result, systems are forced to trade off convergence for performance, or vice versa. To address this, we propose StaleFlow, an RL post-training system that jointly tackles data staleness and skewness. First, to control staleness, StaleFlow introduces a global consistency protocol that tracks the full lifecycle of each trajectory and constrains staleness. Second, to mitigate skewness, StaleFlow re-designs the RL system architecture by constructing data servers for trajectories and parameters to achieve flexible rollout coordination. Subsequently, we develop a suite of staleness-aware, throughput-oriented strategies to enhance system performance. Evaluations show that StaleFlow achieves up to 1.42-2.68× (1.18-1.91× on average) higher throughput than state-of-the-art systems, without compromising convergence. Our source code is available: https://github.com/psrl-project/psrl.