LLM Research Papers: The 2025 List (January to June)

Sebastian Raschka's curated H1 2025 LLM research paper list, broken into three reasoning-focused categories: training (heavy on RL with verifiable rewards), inference-time scaling, and evaluation/understanding. Notable papers covered include DeepSeek-R1 and Kimi k1.5, reflecting the dominant trend of reinforcement learning as the engine behind reasoning model advances. A dense but well-organized reference for anyone tracking the frontier of LLM research.