On the Primacy Bias in RLVR Training
cs.AI
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/minhphucng30-UND/Primacy-bias-RLVR
Terminology
Sources
- From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks
- Algorithms for Learning Kernels Based on Centered Alignment
- What Can Grokking Teach Us About Learning Under Nonstationarity?
- In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning
- Composer 2 Technical Report
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- HybridFlow: A Flexible and Efficient RLHF Framework
- On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents