Collection of papers research in LLM or AI Agent's thinking mechanisms
-
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
Paper • 2509.07980 • Published • 99 -
ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time Compute
Paper • 2509.04475 • Published • 3 -
Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
Paper • 2505.17813 • Published • 57 -
Deep Think with Confidence
Paper • 2508.15260 • Published • 87