Tool use / function calling

GuardAgent

GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning

Superseded baseline#36 of 55 most-superseded · first seen Jun 13, 2024

Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here

1 papers critique it · 0 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites GuardAgent as a baseline.

GuardAgent relies on manually specified rules, which limits its coverage and generalization to predefined scenarios.
ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.