collaborators

8 papers

cs.LG2026

Safin-1: Safety from Within through Memory-Native State Evolution

Ming Zhang, Kaisen Yang, Shu Yu +15

Long-horizon complex tasks require foundation models to accumulate information, maintain internal states, and adapt over extended interactions. Safety should be an intrinsic proper…

cs.AI2026

Teaching Large Language Models When Not to Know: Learning Temporal Critique for Ex-Ante Reasoning

Chenlu Ding, Jiancan Wu, Yanchen Luo +3

Large language models (LLMs) often fail to reason under temporal cutoffs: when prompted to answer from the standpoint of an earlier time, they exploit knowledge that became availab…

cs.AI2026

Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging

Jiabei Liu, Wenyu Mao, Junfei Tan +4

Deep search agents have proven effective in enhancing LLMs by retrieving external knowledge during multi-step reasoning. However, existing methods often generate a single query for…

cs.CL2026

R^2-Mem: Reflective Experience for Memory Search

Xinyuan Wang, Wenyu Mao, Junkang Wu +2

Deep search has recently emerged as a promising paradigm for enabling agents to retrieve fine-grained historical information without heavy memory pre-managed. However, existing dee…

cs.AI2026

Self-ReSET: Learning to Self-Recover from Unsafe Reasoning Trajectories

Dongcheng Zhang, Yi Zhang, Yuxin Chen +3

Large Reasoning Models possess remarkable capabilities for self-correction in general domain; however, they frequently struggle to recover from unsafe reasoning trajectories under…

cs.AI2026

Internalizing Safety Understanding in Large Reasoning Models via Verification

Yi Zhang, Yuxin Chen, Leheng Sheng +4

While explicit Chain-of-Thought (CoT) empowers large reasoning models (LRMs), it enables the generation of riskier final answers. Current alignment paradigms primarily rely on exte…