Thinking Inertia: LLMs Keep Thinking When Told Not To
Paper • 2610.11765 • Published • 219
AI & ML interests
Large language model reasoning, visible chain-of-thought behavior, no-thinking interventions, and evaluation of response-level reasoning.
Recent Activity
View all activity
DianQiao
submitted a
paper to Daily Papers 1 day ago
DianQiao
authored 4
papers 2 days ago
Thinking Inertia: LLMs Keep Thinking When Told Not To
Paper • 2610.11765 • Published • 219
Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering
Paper • 2607.28568 • Published • 191
EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions
Paper • 2606.23654 • Published • 81
Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization
Paper • 2604.12290 • Published • 17
DianQiao
published a
dataset 9 days ago
DianQiao
updated a
dataset 9 days ago