Story
arxiv_agent_systems_research · Oct 3, 2026 · paper
Source brief
COPEX: Benchmarking LLM Robustness to Adversarial Context Across Model Context Protocol Layers
arxiv.orgOct 3, 2026
original source linked
In brief
Large language models increasingly mediate tool use in Model Context Protocol (MCP) systems, where adversarial influence may enter through user instructions, tool schemas, tool outputs, or protocol messages. Existing...
Feed lens
agenteval