No agent system can be accountable without auditability, which requires five dimensions (action recoverability, lifecycle coverage, policy checkability, responsibility attribution, evidence integrity) and mechanisms for detect/enforce/recover.
AGrail: A lifelong agent guardrail with effective and adaptive safety detection
2 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
2
Pith papers citing it
2
external citations · OpenAlex
citation-role summary
baseline 1
citation-polarity summary
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2roles
baseline 1polarities
baseline 1representative citing papers
Position paper claiming that AI safety requires explicit runtime controllability and introducing ControlBench to demonstrate gaps in existing alignment methods.
citing papers explorer
-
Auditable Agents
No agent system can be accountable without auditability, which requires five dimensions (action recoverability, lifecycle coverage, policy checkability, responsibility attribution, evidence integrity) and mechanisms for detect/enforce/recover.
-
Position: AI Safety Requires Effective Controllability
Position paper claiming that AI safety requires explicit runtime controllability and introducing ControlBench to demonstrate gaps in existing alignment methods.