Post-training — page 3

• Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
  arxiv:2601.18734 · 2026-01-26 · text available
• Self-Refine: Iterative Refinement with Self-Feedback
  arxiv:2303.17651 · 2023-03-30 · text available
• Single-stream Policy Optimization
  arxiv:2509.13232 · 2025-09-16 · text available
• Skip-Connected Policy Optimization for Implicit Advantage
  arxiv:2604.08690 · 2026-04-09 · text available
• Soft Adaptive Policy Optimization
  arxiv:2511.20347 · 2025-11-25 · text available
• Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs
  arxiv:2601.11061 · 2026-01-16 · text available
• SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment
  arxiv:2512.02807 · 2025-12-02 · text available
• The Art of Scaling Reinforcement Learning Compute for LLMs
  arxiv:2510.13786 · 2025-10-15 · text available
• The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
  arxiv:2503.02875 · 2025-03-04 · text available
• To Retain or to Adapt? Generalizing Continual Learning
  arxiv:2607.05609 · 2026-07-06 · text available
• Towards Execution-Grounded Automated AI Research
  arxiv:2601.14525 · 2026-01-20 · text available
• TTPO: Test-Time Policy Optimization
  arxiv:2608.27448 · 2026-08-27 · text available
• TTRL: Test-Time Reinforcement Learning
  arxiv:2504.16084 · 2025-04-22 · text available
• Understanding R1-Zero-Like Training: A Critical Perspective
  arxiv:2503.20783 · 2025-03-26 · text available
• Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
  arxiv:2604.02288 · 2026-04-02 · text available
• Unsupervised Elicitation of Language Models
  arxiv:2506.10139 · 2025-06-11 · text available
• Weight-Space Geometry of Offline Reasoning Training
  arxiv:2606.23740 · 2026-06-26 · text available
• When Does Continual Learning Require Learning
  arxiv:2607.07847 · 2026-07-08 · text available
• Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
  arxiv:2603.24472 · 2026-03-25 · text available