Tool-using artificial intelligence (AI) agents, systems that autonomously invoke application programming interfaces (APIs), databases, browsers, and inter-agent protocols such as the Model Context Protocol (MCP), are becoming production infrastructure. Yet the security model governing when an agent is authorized to act...
Large language models (LLMs) deployed as agentic systems capable of tool use, code execution, file manipulation, and multi-step planning inherit and amplify the classical reinforcement learning problem of reward hacking. This survey synthesizes how proxy-based alignment and evaluation failures manifest across modern LL...
