Dynamic Minimax Regret Optimization for Robust LLM Post-Training

arXiv:2610.06329 · cs.LG · Submitted 2026-10-05 · Read on arXiv

cs.LG

Submitted: 2026-10-05

Updated: 2026-10-05

Code: https://github.com/huggingface/trl

Terminology

• Minimax Regret — 1× in this paper · explained in 3 episodes
• Regret — 1× in this paper · explained in 3 episodes

Sources

• The Llama 3 Herd of Models
• Training Verifiers to Solve Math Word Problems
• HybridFlow: A Flexible and Efficient RLHF Framework
• Near-Optimal Algorithms for Group Distributionally Robust Optimization and Beyond
• Qwen3 Technical Report
• Ultra-FineWeb: Efficient Data Filtering and Verification for High-Quality LLM Training Data
• DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-training
• HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks
• RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards
• Qwen2 Technical Report
• Instruction-Following Evaluation for Large Language Models

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