# agent-safety
3 articlestagged with “agent-safety”
AI Agent Safety Evaluation Frameworks
Comprehensive review of agent safety benchmarks including SWE-bench safety, AgentBench, and custom evaluation suites.
frontieragent-safetybenchmarks
LLM Agent Safety Benchmarks
Survey of agent safety benchmarks and evaluation frameworks for assessing autonomous AI system risks.
frontier-researchagent-safetybenchmarksevaluation
Self-Improving Agent Safety Challenges
Security and safety challenges posed by self-improving AI agents that modify their own capabilities.
frontier-researchself-improvingagent-safetyalignment