7 papers · 1 filter
Recursive Environment Scaling for General Long-Horizon Agents
Lingxiao Jing, Zhengbo Jiao, Yichen Xiang +10
We study environment scaling as a way to increase agent-benchmark difficulty while holding core task objectives fixed. Our framework, Recursive Environment Scaling (RES), transform…
EmoRSS: Mitigating Emotion-Induced Over-Refusal in Large Language Models
Shuyi Miao, Yaojin Ma, Chenhang Cui +5
Emotional expression can influence the safety decisions of large language models (LLMs), offering a potential avenue for improving safety alignment. Existing studies have mainly fo…
ACTR: Aligning Thoughts and Responses for Multilingual Safety in Reasoning LLMs
Xianhui Zhang, Jian Yu, Chengyu Xie +6
Ensuring the safety of reasoning large language models (LLMs) across languages is essential for their reliable deployment. However, when exposed to jailbreak attacks in non-high-re…
VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions
Yuxin Chen, Yi Zhang, Zhengzhou Cai +11
Large language models (LLMs) have evolved into interactive agents that collaborate with users in real-world tasks. Effective collaboration in such settings increasingly depends on…
Risky-Bench: Evaluating Agentic Safety Risks in Real-World Life-Assist Deployments
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 through tool use, external…
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…
RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards
Jingnan Zheng, Xiangtian Ji, Yijun Lu +6
Large Language Models (LLMs) continue to exhibit vulnerabilities despite deliberate safety alignment efforts, posing significant risks to users and society. To safeguard against th…