AgentSpec introduces a customizable DSL for runtime enforcement of safety constraints on LLM agents, achieving over 90% prevention of unsafe code actions, zero hazardous embodied actions, and 100% AV compliance in evaluations.
Safeguarding large language models: A survey
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Guardian-as-an-Advisor prepends risk labels and explanations from a guardian model to queries, improving LLM safety compliance and reducing over-refusal while adding minimal compute overhead.
The paper presents a layered method to translate governance objectives from standards such as ISO/IEC 42001 into four control layers for agentic AI, with runtime guardrails limited to observable, determinate, and time-sensitive controls, shown via a procurement-agent case study.
citing papers explorer
-
AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents
AgentSpec introduces a customizable DSL for runtime enforcement of safety constraints on LLM agents, achieving over 90% prevention of unsafe code actions, zero hazardous embodied actions, and 100% AV compliance in evaluations.
-
Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs
Guardian-as-an-Advisor prepends risk labels and explanations from a guardian model to queries, improving LLM safety compliance and reducing over-refusal while adding minimal compute overhead.
-
From Governance Norms to Enforceable Controls: A Layered Translation Method for Runtime Guardrails in Agentic AI
The paper presents a layered method to translate governance objectives from standards such as ISO/IEC 42001 into four control layers for agentic AI, with runtime guardrails limited to observable, determinate, and time-sensitive controls, shown via a procurement-agent case study.