Cite
Notes
Only stored in your browser.
Attribution
AgentSPEX: An Agent SPecification and EXecution Language
arXiv 2026
One Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious Intent
The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search
arXiv 2025
from 3 papers
Eli Chien
Pan Li
Pin-Yu Chen
Rongzhe Wei
Ruihan Wu
Xinjie Shen
Bo Li
Haoyu Wang
Jerry Huang
Jiarui Yao