Chain-of-Thought

ReShift: Aha-Moment-Driven Reasoning-Level Backdoor Attacks on Vision–Language Models
We propose ReShift, the first aha-moment-driven reasoning-level backdoor framework for Vision–Language Models that redirects chain-of-thought trajectories while preserving surface-level coherence.
Zhihao Dou, Qinjian Zhao, Zhiqiang Gao, Sumon Biswas
Cite
Plan Then Action: High-Level Planning Guidance Reinforcement Learning for LLM Reasoning
We propose PTA-GRPO, a two-stage framework that improves LLM reasoning by combining high-level planning guidance with guidance-aware reinforcement learning.
Zhihao Dou, Qinjian Zhao, Zhongwei Wan, Dinggen Zhang, Weida Wang, Towsif Raiyan, Benteng Chen, Qingtao Pan, Yang Ouyang, Zhiqiang Gao, Shufei Zhang, Sumon Biswas
Cite ArXiv