ForeMoE uses routing foresight from the rollout stage to enable micro-step load balancing in MoE RL post-training via a hierarchical planner and transfer engine, claiming up to 1.45x speedup on 64 GPUs.
Part ii: Roll flash–accelerating rlvr and agentic training with asynchrony
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Freshness-Aware PER augments prioritized experience replay with exponential age decay based on effective sample size to enable successful reuse of trajectories in LLM and VLM reinforcement learning, outperforming on-policy baselines on agentic tasks.
NExt accelerates RLVR training for LLMs by nonlinearly extrapolating low-rank parameter trajectories extracted from LoRA runs.
SAO stabilizes asynchronous RL for LLMs by replacing group-wise sampling with single-rollout updates, token-level importance sampling, and targeted value-model training, outperforming GRPO on reasoning and coding benchmarks.
ROSE is a system for cooperative elasticity that co-locates serving and rollout models on shared GPUs, delivering 1.3-3.3x higher end-to-end throughput than fixed-resource baselines while preserving serving SLOs.
Seer improves synchronous LLM RL rollout throughput by up to 2.04x and reduces long-tail latency by 72-94% via divided rollout, context-aware scheduling, and adaptive grouped speculative decoding based on prompt similarity observations.
DARTS accelerates LLM RL training up to 1.77x by distribution-aware trajectory sampling and adaptive redundancy allocation that shapes rollouts toward conciseness without performance loss.
citing papers explorer
-
Harnessing Routing Foresight for Micro-step-level MoE load balancing in RL Post-training
ForeMoE uses routing foresight from the rollout stage to enable micro-step load balancing in MoE RL post-training via a hierarchical planner and transfer engine, claiming up to 1.45x speedup on 64 GPUs.
-
Freshness-Aware Prioritized Experience Replay for LLM/VLM Reinforcement Learning
Freshness-Aware PER augments prioritized experience replay with exponential age decay based on effective sample size to enable successful reuse of trajectories in LLM and VLM reinforcement learning, outperforming on-policy baselines on agentic tasks.
-
Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration
NExt accelerates RLVR training for LLMs by nonlinearly extrapolating low-rank parameter trajectories extracted from LoRA runs.
-
Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning
SAO stabilizes asynchronous RL for LLMs by replacing group-wise sampling with single-rollout updates, token-level importance sampling, and targeted value-model training, outperforming GRPO on reasoning and coding benchmarks.
-
ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL
ROSE is a system for cooperative elasticity that co-locates serving and rollout models on shared GPUs, delivering 1.3-3.3x higher end-to-end throughput than fixed-resource baselines while preserving serving SLOs.
-
Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning
Seer improves synchronous LLM RL rollout throughput by up to 2.04x and reduces long-tail latency by 72-94% via divided rollout, context-aware scheduling, and adaptive grouped speculative decoding based on prompt similarity observations.
-
DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning
DARTS accelerates LLM RL training up to 1.77x by distribution-aware trajectory sampling and adaptive redundancy allocation that shapes rollouts toward conciseness without performance loss.
- AsyncWebRL: Efficient Asynchronous Reinforcement Learning for Multi-Step Visual Web Agents