Skill-augmented agents load reusable skills as persistent runtime context, improving task performance but also giving malicious skills a durable channel for steering future actions. Such skills may leak secrets, corrupt code, bypass approvals, or stage data for exfiltration only after a concrete user task and workspace...
Xiao-Fan Yang, Ziqi Miao, Chen Qian et al.· 0 citations
As large language models (LLMs) acquire advanced biological design capabilities, they offer substantial research benefits but simultaneously introduce severe dual-use risks, such as engineering enhanced pathogens or drug-resistant bacteria. While biosecurity frameworks recognize these threats, the actual risk of LLMs e...
Yu-Zhen Wang, Chun-Xiao Li, Bai-Chen Le et al.· 0 citations
TabSieve, a select-then-predict framework that makes evidence usage explicit and auditable, and introduces TAB-GRPO, a reinforcement learning recipe that jointly optimizes evidence selection and prediction correctness with separate rewards, and stabilizes mixed regression and classification training via dynamic task-ad...
Yong-Yao Wang, Ziqi Miao, Lu Yang et al.· arXiv.org· 5 citations
KC-Bench is introduced, a controlled multi-turn benchmark for measuring model-level behavior across world-knowledge conflicts, input inconsistencies, and multi-source temporal conflicts, and provides a reproducible diagnostic for developing conflict-aware reasoning and execution safeguards.
Yaxing Lyu, Sheng-Jie Zhou, B. Toh et al.· 2 citations
This work proposes Defense-as-Skill, a defense paradigm that implements the runtime guard itself as an installable, inspectable, and editable skill, and demonstrates transfer across victim models, held-out risk families, and external benchmarks, as well as retained protection against adaptive attackers.
Xiao-Fan Yang, Ziqi Miao, Dian-Bo Sui et al.· 0 citations
SCHEMA reveals that hallucinations concentrate at a small set of highly connected knowledge hubs, and that final-answer accuracy decouples from trajectory honesty; models often reach correct conclusions through structurally flawed reasoning.
Xinshun Feng, Ziqi Miao, Li-Jun Li et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
