Understanding Enrichment in Reinforcement Learning

arXiv:2610.02846 · cs.LG · Submitted 2026-10-02 · Read on arXiv

cs.LG

Submitted: 2026-10-02

Updated: 2026-10-02

Terminology

• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information
• Learning to Reason at the Frontier of Learnability
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs
• Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• Tulu 3: Pushing Frontiers in Open Language Model Post-Training
• Process Reward Informed Tree Rollout for Effective Multi-Turn RL
• LLM-CoT Enhanced Graph Neural Recommendation with Harmonized Group Policy Optimization
• AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset
• Policy Gradient with Active Importance Sampling
• DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
• Boosting LLM Exploration via Weak-Model Guidance in RLVR
• Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
• Qwen3 Technical Report
• ADHint: Adaptive Hints with Difficulty Priors for Reinforcement Learning
• Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective
• Probabilistic Inference in Language Models via Twisted Sequential Monte Carlo

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks