DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards
cs.LG, cs.AI
Submitted: 2026-05-08
Updated: 2026-10-28
Comments: The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS 2026)
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Adaptive Stratified Sampling for Monte-Carlo integration of Differentiable functions
- Evaluating Large Language Models Trained on Code
- SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization
- Training Verifiers to Solve Math Word Problems
- How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization
- The Llama 3 Herd of Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Measuring Mathematical Problem Solving With the MATH Dataset
- Training Compute-Optimal Large Language Models
- Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
- Doubly Robust Off-policy Value Evaluation for Reinforcement Learning
- Scaling Laws for Neural Language Models
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- LIMR: Less is More for RL Scaling
- Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation
- s1: Simple test-time scaling
- Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewards
- Carbon Emissions and Large Neural Network Training
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning