3 papers
cs.LG2025
Extending Test-Time Scaling: A 3D Perspective with Context, Batch, and Turn
Chao Yu, Qixin Tan, Jiaxuan Gao +7
Reasoning reinforcement learning (RL) has recently revealed a new scaling effect: test-time scaling. Thinking models such as R1 and o1 improve their reasoning accuracy at test time…
cs.CL2025
How Far Are We from Optimal Reasoning Efficiency?
Jiaxuan Gao, Shu Yan, Qixin Tan +6
Large Reasoning Models (LRMs) demonstrate remarkable problem-solving capabilities through extended Chain-of-Thought (CoT) reasoning but often produce excessively verbose and redund…
cs.CR2025
AED: Automatic Discovery of Effective and Diverse Vulnerabilities for Autonomous Driving Policy with Large Language Models
Le Qiu, Zelai Xu, Qixin Tan +3
Assessing the safety of autonomous driving policy is of great importance, and reinforcement learning (RL) has emerged as a powerful method for discovering critical vulnerabilities…