When Tools Silently Lie: Evaluating and Mitigating Blind Compliance in Tool-Augmented Data Agents
ToxicBench finds poisoned tool outputs cut data-agent success 26 to 39 points, with wrong answers adopted after checks.
1 stories, newest first · one card per story
ToxicBench finds poisoned tool outputs cut data-agent success 26 to 39 points, with wrong answers adopted after checks.
Today 949 readers · 1.3K views · 1K reads · all time 159K views