Teach to Learn: Hint Annealing for Self-improving LLM Reasoning
cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Sources
- Self-Evolving Curriculum for LLM Reasoning
- Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs
- Adam: A Method for Stochastic Optimization
- Self-Hinting Language Models Enhance Reinforcement Learning
- Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning
- POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- HybridFlow: A Flexible and Efficient RLHF Framework
- Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
- Qwen3 Technical Report
- Learning to Hint for Reinforcement Learning
- Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning
- KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance
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