8 papers
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…
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…
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…
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…
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…
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…