BRAT: Bounded Residual-Aligned Training for Stable Multi-Pass LLM Post-Training
cs.LG
Submitted: 2026-11-07
Updated: 2026-11-07
Terminology
Sources
- MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
- Training Verifiers to Solve Math Word Problems
- The Llama 3 Herd of Models
- Soft Adaptive Policy Optimization
- Reinforced Self-Training (ReST) for Language Modeling
- Online Causal Kalman Filtering for Stable and Effective Policy Optimization
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- Fibration Policy Optimization
- Understanding R1-Zero-Like Training: A Critical Perspective
- Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
- Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Qwen3 Technical Report
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- Beyond KL Divergence: Policy Optimization with Flexible Bregman Divergences for LLM Reasoning
- Improving Sampling Efficiency in RLVR through Adaptive Rollout and Response Reuse
- Group Sequence Policy Optimization
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis