reasoning

Purified OPSD: Fixing Self-Distillation for Long Chain-of-Thought Models

UserHarness: Reconstructing User Minds for Stronger Agent Theory of Mind

Context-CoT: Teaching LLMs to Actually Learn from Context

Quantum Knowledge Graphs: Context-Dependent Triplet Validity

Learning to Reason with Insight for Informal Theorem Proving

Z3: SMT Solving for Software Verification and Constraint Reasoning

Large Language Models: The Engine Behind Modern AI Agents