The Model Knows Another Way: Strategy Switching for Effective RLVR Exploration
cs.AI
Submitted: 2026-09-27
Updated: 2026-09-27
Comments: 23 pages, 5 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
- Select and Improve: Understanding the Mechanics of Post-Training for Reasoning
- SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs
- Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR
- Adaptive Guidance Accelerates Reinforcement Learning of Reasoning Models
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- How You Begin is How You Reason: Driving Exploration in RLVR via Prefix-Tuned Priors
- Learning to Reason under Off-Policy Guidance
- Qwen2.5 Technical Report
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
- Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
- BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning
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