Post-training — page 2

• LADDER: Self-Improving LLMs Through Recursive Problem Decomposition
  arxiv:2503.00735 · 2025-03-02 · text available
• Latent On-Policy Self-Distillation
  arxiv:2608.13040 · 2026-08-13 · text available
• Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards
  arxiv:2606.18810 · 2026-06-17 · text available
• Learning to Discover at Test Time
  arxiv:2601.16175 · 2026-01-22 · text available
• Learning to Reason without External Rewards
  arxiv:2505.19590 · 2025-05-26 · text available
• LoRA Without Regret (Thinking Machines)
  url:thinkingmachines.ai/blog/lora · 2025-09-29 · metadata only
• MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
  arxiv:2506.13585 · 2025-06-16 · text available
• Oat-Zero: reproducing R1-Zero and analyzing self-reflection
  url:oatllm.notion.site/oat-zero · 2025-03-21 · metadata only
• On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification
  arxiv:2508.05629 · 2025-08-07 · text available
• OPRD: On-Policy Representation Distillation
  arxiv:2606.06021 · 2026-06-04 · text available
• Reasoning with Sampling: Your Base Model is Smarter Than You Think
  arxiv:2510.14901 · 2025-10-16 · text available
• Recursive Self-Improvement via On-Policy Distillation for Reasoning
  arxiv:2609.30652 · 2026-09-25 · text available
• Reinforced Efficient Reasoning via Semantically Diverse Exploration
  arxiv:2601.05053 · 2026-01-08 · text available
• Reinforcement Learning via Self-Distillation
  arxiv:2601.20802 · 2026-01-28 · text available
• Representation-Based Exploration for Language Models: From Test-Time to Post-Training
  arxiv:2510.11686 · 2025-10-13 · text available
• Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
  arxiv:2604.13016 · 2026-04-14 · text available
• Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability Learning
  arxiv:2605.06241 · 2026-05-07 · text available
• Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
  arxiv:2603.25562 · 2026-03-26 · text available
• Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective
  arxiv:2605.12969 · 2026-05-13 · text available
• RIFT: A RubrIc Failure Mode Taxonomy and Automated Diagnostics
  arxiv:2604.01375 · 2026-04-01 · text available
• RLTL;DR: Self-improvement by Internalizing Self-generated Feedback
  arxiv:2609.37633 · 2026-09-29 · text available
• RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments
  arxiv:2511.07317 · 2025-11-10 · text available
• Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning
  arxiv:2402.13669 · 2024-02-21 · text available
• Self-Distillation Enables Continual Learning
  arxiv:2601.19897 · 2026-01-27 · text available