4 papers · 1 filter
CreepScope: Measuring Post-Use Authorization Exposure in Tool-Using Agents
Haoran Yu, Lifei Liu, Danping Zhang +4
Authorization checks at individual tool calls do not reveal how long earlier authority remains usable. We study this lifecycle failure as privilege creep: a capability stays reacha…
Attesting Outputs and Delegation Ancestry in Multi-Agent AI Systems
Lifei Liu, Haoran Yu
Multi-agent applications delegate work across independently operated deployers. After an incident, a verifier must answer two questions: which deployer released the reported bytes,…
Phantom Guardrails: When Self-Improving Agent Harnesses Fix Failures That Never Happened
Su Wang, Pin Qian, Yifan Lin +5
Self-improving AI agents are designed to learn from their mistakes. We show they can also hallucinate mistakes that never happened. We study this failure mode in automated harness…
ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation
Xiaochong Jiang, Shiqi Yang, Ziwei Li +3
Tool-using agents increasingly operate in open-ended deployment environments, where they compose file systems, web APIs, code interpreters, and enterprise services at runtime. This…