5 papers
Risky-Bench: Probing Agentic Safety Risks under Real-World Deployment
Jingnan Zheng, Yanzhen Luo, Jingjun Xu +8
Large Language Models (LLMs) are increasingly deployed as agents that operate in real-world environments, introducing safety risks beyond linguistic harm. Existing agent safety eva…
Self-Guard: Defending Large Reasoning Models via enhanced self-reflection
Jingnan Zheng, Jingjun Xu, Yanzhen Luo +6
The emergence of Large Reasoning Models (LRMs) introduces a new paradigm of explicit reasoning, enabling remarkable advances yet posing unique risks such as reasoning manipulation…
Understanding Multilingualism in Mixture-of-Experts LLMs: Routing Mechanism, Expert Specialization, and Layerwise Steering
Yuxin Chen, Zhengzhou Cai, Xiangtian Ji +4
Mixture-of-Experts (MoE) architectures have shown strong multilingual capabilities, yet the internal mechanisms underlying performance gains and cross-language differences remain i…
LIMI: Less is More for Agency
Yang Xiao, Mohan Jiang, Jie Sun +18
We define Agency as the emergent capacity of AI systems to function as autonomous agents actively discovering problems, formulating hypotheses, and executing solutions through self…
AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning
Yi Zhang, An Zhang, XiuYu Zhang +4
Large language models (LLMs), despite possessing latent safety understanding from their vast pretraining data, remain vulnerable to generating harmful content and exhibit issues su…