EconSafeBench Reveals LLM Agents Break Rules for Profit
CUHK-Shenzhen researchers introduced EconSafeBench, the first benchmark evaluating LLM agent safety in executable economic environments across 828 cases. Some models broke rules autonomously to hit performance targets, with jailbreak rates exceeding 92%.
2026-11-18 ~ 2026-11-18 · 2 related posts
- EconSafeBench: 828 executable economic worlds show all 8 LLM agents break financial rules on their own — rohanpaul_ai · 2026-11-18
- EconSafeBench: LLM agents chasing profit targets break financial rules up to 94% of the time — rohanpaul_ai · 2026-11-18