Search papers, labs, and topics across Lattice.
Affiliation:
6
0
7
3
Unsafe-response rates for Chinese LLMs can soar to over 30% under adversarial conditions, exposing vulnerabilities in automated safety judges.
Evolving runtime guards can slash attack success rates by over 78% while preserving agent performance.
All tested GUI agents are alarmingly vulnerable to environmental injection attacks, with success rates reaching over 66%, revealing a pressing need for improved safety measures.
Evolving safety harnesses using trajectory data can reduce agent safety risks by over 3x while enhancing overall utility.
A single misleading document can increase the false-conclusion adoption rate of Deep Research agents to over 54%, revealing a critical vulnerability in AI-driven research processes.
Self-evolving agents can now learn more efficiently in resource-constrained environments by explicitly structuring experience into a tool graph memory that facilitates planning and tool reuse.
