Search papers, labs, and topics across Lattice.
Chinese Academy of Sciences, University of Chinese Academy of Sciences
3
0
6
Over-privileged tool selection is alarmingly common in LLM agents, often triggered by transient failures, raising critical safety concerns in autonomous decision-making.
Pre-load auditing of Agent Skills can achieve >97% accuracy in detecting malicious intent, even against semantics-preserving rewrites, by combining role-aware evidence extraction with semantic verification.
Decoupling fact injection from text generation lets you edit LLMs with greater precision, improving fine-grained question answering without sacrificing overall editing performance.
