Bridging Risk Approximation Gaps in Model Predictive Task Sampling via In-Context Modeling
cs.AI, cs.LG
Submitted: 2026-10-10
Updated: 2026-10-10
Sources
- GPT-4 Technical Report
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
- Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
- Model Predictive Task Sampling for Efficient and Robust Adaptation
- Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments
- Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning
- Auto-Encoding Variational Bayes
- Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
- Qwen3 Technical Report
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- A Tutorial on Meta-Reinforcement Learning
- Domain Randomization via Entropy Maximization
- VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning
- Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning
- TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning
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