conftrace_

safety vulnerabilities

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

interlocutor awareness (1) defense strategies (1) reasoning capabilities (1) attack surface (1) multi-agent system (1) large language model (1) defense strategy (1) large reasoning model (1) safety risk (1) defense mechanism (1)

Papers

Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models EMNLP 2025 Safety in Large Reasoning Models: A Survey EMNLP 2025