← Back to all news
arXiv AI By Haoyu Hu, Xuandong Zhao, Xuhai "Orson'' Xu, Nori Jacoby

DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards

Read the original on arXiv AI →

DUET is a token‑budget allocation method for reinforcement learning with verifiable rewards that jointly optimizes which prompts receive rollouts and how long each rollout runs. By using a lightweight surrogate to assign rollouts and a marker‑gated abort rule to stop them, DUET improves reasoning quality and reduces training time compared to full‑budget GRPO and other baseline methods. Experiments on Qwen3‑1.7B and other LLMs show that DUET outperforms baselines even with only 50% of the token budget, achieving up to 2.51× speedup while maintaining or improving performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Jul 16

Where Should RL Post-Training Compute Go? Model Size, Search, Learning, and Feedback

arXiv:2607. 13389v1 Announce Type: new Abstract: Reinforcement Learning (RL) post-training is increasingly used to adapt foundation models for reasoning, planning, and feedback-driven robot-learning pipelines, but constrained post-training resources are often summarized by a single total FLOP budget.

By Patrick Wilhelm, Odej Kao
reinforcement-learningroboticsfine-tuning
More like this →
arXiv Machine Learning
Jul 30

Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR

arXiv:2607. 26253v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is bottlenecked by rollout generation, yet many sampled prompts produce saturated groups (all responses correct or all incorrect) whose zero reward variance yields no policy-gradient signal.

By Pixel Nomand, Elena Voss, Marcus Hale, Sofia Reyes
reinforcement-learning
More like this →
arXiv Machine Learning
Oct 12

S$^3$R: Fast and Faithful RL Rollouts via Self-Sparse Speculative Decoding

The paper introduces Self‑Sparse Speculative Rollouts (S$^3$R), a method that uses sparse attention to propose tokens and then verifies them with full attention, thereby reducing KV‑cache traffic while preserving the dense‑policy distribution for reinforcement learning rollouts. S$^3$R eliminates the need for a separate drafter by sharing policy parameters between drafting and verification, and a KV‑aware scheduler limits cache thrashing to maintain parallelism. Experiments on long‑context mathematical reasoning with the Qwen3 model show that S$^3$R achieves 1.35–1.39× higher end‑to‑end training throughput with comparable task performance.

By Yuhang He, Hongyu Ge, Zihan Lin, Siyi Liu, Yongqi Zhang
reinforcement-learningefficiencybenchmarks
More like this →