# Bidirectional Resource Scheduling for Disaggregated and Asynchronous RL Post-Training

arXiv: https://arxiv.org/abs/2607.09207 · HTML: https://mlsanity.com/paper/2607.09207/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2026.

## Built on by (most cited first, 6 of 6)

- [Deconstructing Off-Policy Ratios: Entropy-Normalized Trust Regions for Asynchronous Reinforcement Learning](https://mlsanity.com/paper/2607.22186/) (2026)
- [LeanGRPO: Eliminating Redundant Recomputation in Diffusion RL](https://mlsanity.com/paper/2609.03528/) (2026)
- [BRACE: Anchored Bellman-Residual Correction for Stale Critics in Asynchronous RL](https://mlsanity.com/paper/2609.09783/) (2026)
- [Rollout Efficiency in Reinforcement Learning for Reasoning Large Language Models: A Taxonomy and Future Directions](https://mlsanity.com/paper/2609.25463/) (2026)
- [PEARL: Adaptive Prefill-Decode Execution with Elasticity for Agentic Reinforcement Learning](https://mlsanity.com/paper/2609.35158/) (2026)
- [Efficient Resource-Shiftable RL Post-training with Generative Rewards](https://mlsanity.com/paper/2610.16866/) (2026)

## Abstract (arXiv)

It is well established that the reasoning capabilities of large language models (LLMs) can be improved by applying reinforcement learning (RL) in a post-training stage. In a standard RL iteration, the current model (the policy) generates experience through rollouts, and the resulting data is then used to update the policy during training. High-performance RL frameworks such as StreamRL and AReaL employ a disaggregated architecture and asynchronous rollouts to better exploit both rollout and training resources, thereby increasing overall system throughput. Nonetheless, across varying RL setups (e.g., hardware configurations, model scales, staleness levels, and hyperparameters) and under changing workloads, it remains common for both rollout and training resources to experience idle periods. In this paper, we present BiDiRL, a hybrid time-space multiplexing architecture for asynchronous, disaggregated RL designed to reduce resource idleness. First, we develop a hot-switch runtime that enables rapid switching between rollout and training resources with negligible overhead. Second, we propose a static, scheduling-aware planner based on time-performance modeling that chooses a hot-switch-friendly resource partition, so that rollout and training durations are roughly balanced at a coarse level. Third, at execution time, we introduce a bidirectional scheduler that further exploits runtime bubbles through fine-grained resource switching, allowing the bottleneck stage to temporarily borrow idle resources from the other pool. Across a wide range of workloads, datasets, and models on two 32-GPU testbeds, BiDiRL increases RL training throughput by up to 1.94x compared with RL systems including veRL, AReaL, and ROLL, without affecting convergence behavior.