AgentDrift: Unsafe Recommendation Drift Under Tool Corruption Hidden by Ranking Metrics in LLM Agents
arXiv:2603.12564v1 Announce Type: new Abstract: Tool-augmented LLM agents increasingly serve as multi-turn advisors in high-stakes domains, yet their evaluation relies on ranking-quality metrics that measure …
Zekun Wu, Adriano Koshiyama, Sahan Bulathwela, Maria Perez-Ortiz
15 views