Method Drift›Tool use / function calling
Superseded baseline#48 of 55 most-superseded
ShieldAgent
ShieldAgent: Shielding Agents via Verifiable Safety Policy ReasoningTool use / function calling · first seen Mar 26, 2025
superseded — cited as a baseline and beaten by newer methods
1 papers critique it · 0 beat it on benchmarks
What papers say
Verbatim critique sentences, each from a paper that cites ShieldAgent as a baseline.
“ShieldAgent and AGrail produce safety judgments via complex reasoning and verification pipelines, incurring high latency that makes them impractical for step-level monitoring of tool invocation in LLM-based agents.”
— ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback
Newer alternatives
Recent methods in the same sub-problem, not yet superseded in the knowledge base.