Learning to Steer, Steering to See: Unveiling the Geometry of RLVR in Large Language Models via Trainable Vectors
cs.LG, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/caiyuchen-ustc/On
Terminology
Sources
- On Predictability of Reinforcement Learning Dynamics for Large Language Models
- Learning to Foresee: Unveiling the Unlocking Efficiency of On-Policy Distillation
- Process Reinforcement through Implicit Rewards
- The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models
- SciKnowEval: Evaluating Multi-level Scientific Knowledge of Large Language Models
- Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
- Editing Models with Task Arithmetic
- Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
- Let's Verify Step by Step
- AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset
- Training language models to follow instructions with human feedback
- Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
- A Survey of On-Policy Distillation for Large Language Models
- Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning
- Kimi K3: Open Frontier Intelligence
- The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
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