conftrace_

llm agent safety

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

autonomous agent (2) adaptive safety detection (1) lifelong guardrail (1) risk mitigation (1) systemic risk (1) causal influence (1) large language model (1) safety detection (1) task-specific risk (1) causal diagram (1)

Papers

AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection ACL 2025 Enhancing LLM Agent Safety via Causal Influence Prompting ACL 2025