Reasoning

2026 3

Reading Model States Through Newline Tokens: What Word Salad Chopper Reveals
Making Agents Practical: Structured Output and Constrained Decoding for LLMs
The Essence of LLM Reasoning and Training: From Surrogates to Reinforcement Learning Geometry

2024 1

Prompt Engineering and In-Context Learning: Foundations, Technique Map, and Practical Workflows

1