Author

Lifei Liu

Observed name: Liu, Lifei

Institutions: Wichita State University, Carnegie Mellon University

Observed institutions: Wichita State University, Carnegie Mellon University

OpenAlex ID: A5148917135

Operational Reframing and Approval-Framed Delegation in Multi-Agent LLM Safety

2026 · Liu, Lifei, Yu, Haoran, et al. · arXiv (Cornell University) · 3

When Should Active RAG Retrieve? A Budget-Aware Evaluation of Utility, Calibration, and Cost

2026 · Qian, Pin, Wang, Su, et al. · arXiv (Cornell University) · 2

Attesting Outputs and Delegation Ancestry in Multi-Agent AI Systems

2026 · Liu, Lifei, Yu, Haoran · arXiv (Cornell University) · 1

VERA: Authority-Preserving Edge Revocation for Federated AI-Agent Workflows

2026 · Liu, Lifei, Yu, Haoran, et al. · arXiv (Cornell University) · 1

Phantom Guardrails: When Self-Improving Agent Harnesses Fix Failures That Never Happened

2026 · Wang, Su, Qian, Pin, et al. · arXiv (Cornell University) · 1

Revocation Is Not Complete at Receipt: An Executable Outcome Contract for Distributed Agent-Tool Gateways

2026 · Liu, Lifei, Yu, Haoran, et al. · arXiv (Cornell University)

CreepScope: Measuring Post-Use Authorization Exposure in Tool-Using Agents

2026 · Yu, Haoran, Liu, Lifei, et al. · arXiv (Cornell University)

Cost-Aware Post-Hoc Deferral Under Calibration and Shift: An Environmental AI Case Study

2026 · Yu, Haoran, Liu, Lifei, et al. · arXiv (Cornell University)

ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation

2026 · Jiang, Xiaochong, Yang, Shiqi, et al. · arXiv (Cornell University)

Works count: 9

Citation count: 8

H-index: 2

I10-index: