Story
arxiv_cs_ai · Nov 7, 2026 · paper
Source brief
Tail-risk-aware Agent Safety: Constraining Tail Risks Across Multi-step LLM Agent Workflows
arxiv.orgNov 7, 2026
original source linked
In brief
LLM-based agents extend LLMs with tool calls, memory, planning, and retrieval to act in external environments, but they are vulnerable to attacks at different workflow steps. Existing defenses, including prompt engine...
Feed lens
agenteval