3 citations · 3 across the 4 of their papers we have counts for
5 papers
SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents
Xiaoyu Xu, Zi Liang, Minxin Du +4
Tool-using language-model agents select and execute third-party artifacts. Different implementations can return the requested output while producing hidden execution effects that t…
When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents
Xiaoyu Xu, Minxin Du, Qipeng Xie +3
Personalized LLM agents maintain persistent cross-session state to support long-horizon collaboration. Yet, this persistence introduces a subtle but critical security vulnerability…
Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding
Jiaqi Tang, Jianmin Chen, Wei Wei +7
Multimodal Large Language Models struggle to maintain reliable performance under extreme real-world visual degradations, which impede their practical robustness. Existing robust ML…
Where LLM Agents Fail and How They can Learn From Failures
Kunlun Zhu, Zijia Liu, Bingxuan Li +15
Large Language Model (LLM) agents, which integrate planning, memory, reflection, and tool-use modules, have shown promise in solving complex, multi-step tasks. Yet their sophistica…
Compliance-to-Code: Enhancing Financial Compliance Checking via Code Generation
Siyuan Li, Jian Chen, Rui Yao +8
Nowadays, regulatory compliance has become a cornerstone of corporate governance, ensuring adherence to systematic legal frameworks. At its core, financial regulations often compri…