MENTOR: Learning from Failure with On-Policy Pedagogical Intervention
cs.AI
Submitted: 2026-10-09
Updated: 2026-10-09
Sources
- Program Synthesis with Large Language Models
- Evaluating Large Language Models Trained on Code
- Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs
- The Llama 3 Herd of Models
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
- DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
- Measuring Massive Multitask Language Understanding
- Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level
- Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
- QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation
- GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
- Distillation Policy Optimization
- Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- A Survey of On-Policy Distillation for Large Language Models
- Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts
- Critique-RL: Training Language Models for Critiquing through Two-Stage Reinforcement Learning
- Teaching Language Models to Critique via Reinforcement Learning
- Qwen3 Technical Report
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