The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity Paper • 2506.06941 • Published Jun 7 • 15
SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training Paper • 2310.02227 • Published Oct 3, 2023
Execution-based Code Generation using Deep Reinforcement Learning Paper • 2301.13816 • Published Jan 31, 2023 • 2