LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models

arXiv:2607.28077 · cs.CL · Submitted 2026-07-30 · Read on arXiv

cs.CL

Submitted: 2026-07-30

Updated: 2026-09-16

Comments: 15pages

Code: https://github.com/ShuangLiangX/LEEPS

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• GRPO — 34× in this paper · explained in 6 episodes
• Benchmark — 26× in this paper · explained in 2 episodes
• Reinforcement Learning — 18× in this paper · explained in 4 episodes
• RLVR — 17× in this paper · explained in 2 episodes
• AUROC — 16× in this paper · explained in 3 episodes
• Calibration — 7× in this paper · explained in 7 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Verifiable Rewards — 6× in this paper · explained in 2 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Generalization — 3× in this paper · explained in 13 episodes
• Papers — 3× in this paper · explained in 3 episodes
• Verifier — 3× in this paper · explained in 2 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Group Relative Policy Optimization — 2× in this paper
• Group Relative Policy Optimization (GRPO) — 2× in this paper · explained in 6 episodes
• Hyperparameters — 2× in this paper · explained in 2 episodes
• Sample Efficiency — 2× in this paper · explained in 7 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Ablation Study — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Evaluation Protocol — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• GRPO Objective — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes
• Weight Decay — 1× in this paper · explained in 2 episodes

Sources

• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
• No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes
• Self-Evolving Curriculum for LLM Reasoning
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Training Verifiers to Solve Math Word Problems
• How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization
• Prompt Curriculum Learning for Efficient LLM Post-Training
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Measuring Mathematical Problem Solving With the MATH Dataset
• Tulu 3: Pushing Frontiers in Open Language Model Post-Training
• Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models
• Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning
• GPQA: A Graduate-Level Google-Proof Q&A Benchmark
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuning
• Efficient Reinforcement Finetuning via Adaptive Curriculum Learning
• FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient Training R1-like Reasoning Models
• Kimi k1.5: Scaling Reinforcement Learning with LLMs
• Solving math word problems with process- and outcome-based feedback

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering