04:00
2026-07-31
machinebrief.com
artificial-intelligence
Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game
A new open-source benchmark framework, ParliamentBench, based on the social deduction game Secret Hitler, evaluates whether large language models (LLMs) can deceive, persuade, and reason under informa…