Balancing Reference Guidance and Free Generation in Trajectory Rollouts for Reasoning RL
cs.AI
Submitted: 2026-10-08
Updated: 2026-10-08
Sources
- Max Out GRPO Signal: Adaptive Trace Prefix Control for Hard Reasoning Problems
- Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO
- What is the objective of reasoning with reinforcement learning?
- Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs
- Binary Rewards and Reinforcement Learning: Fundamental Challenges
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling
- Reinforcement Learning via Self-Distillation
- OpenAI o1 System Card
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- Learning Robust Reasoning through Guided Adversarial Self-Play
- Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding
- Self-Hinting Language Models Enhance Reinforcement Learning
- SuperRL: Reinforcement Learning with Supervision to Boost Language Model Reasoning
- Restoring the Sweet Spot: Pass-Rate Weighted Self-Distillation for LLM Reasoning
- GHPO: Adaptive Guidance for Stable and Efficient LLM Reinforcement Learning
- Towards a Unified View of Large Language Model Post-Training
- NGRPO: Negative-enhanced Group Relative Policy Optimization
- Adaptive Guidance Accelerates Reinforcement Learning of Reasoning Models
- Gradient Starvation in Binary-Reward GRPO: Why Group-Mean Centering Fails and Why the Simplest Fix Works
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems