Tool use / function calling
GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here
1 papers critique it · 0 beat it on benchmarks
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.
Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.