5 papers
PROVISO: Provenance-Informed Action Selection for Secure LLM Agents
Bo Yan, Qi Zhang, Ziwen Kan +2
LLM agents act on the external world through tools and third-party skills, so a single executed action can cause irreversible harm. Existing defenses judge a proposed action withou…
Broken isospectrality in inverted black hole potentials and the emergence of Efimov scaling
Umer Shahzad, Sebastian H. Völkel
Are the inverted Regge-Wheeler and Zerilli potentials arising in Mashhoon's bound-state approach to black-hole quasinormal modes isospectral? Extending previous numerical and analy…
PatientWM: Towards Generalizable Clinical World Models via Unified Patient States
Ziwen Kan, Jie Peng, Bo Yan +5
Clinical decisions depend on anticipating how a patient's condition will evolve as treatment is adjusted and new evidence becomes available. Existing medical world models capture p…
The Menu Is an Execution Prior: State-Path Tool Menus for Online Agents
Bo Yan, Weikai Lin, Song Wang
Language models act through tools, yet practical agents face libraries containing thousands of interfaces. We introduce the tool menu as the short, ordered subset of available tool…
SafeDream: Safety World Model for Proactive Early Jailbreak Detection
Bo Yan, Weikai Lin, Yada Zhu +1
Multi-turn jailbreak attacks progressively erode LLM safety alignment across seemingly innocuous conversation turns, achieving success rates exceeding 90% against state-of-the-art…