Model Releases
Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Game
arXiv:2607.28146v1 Announce Type: new Abstract: As large language models (LLMs) are deployed as agents in high-stakes settings, such as medical and legal systems, understanding their deceptive capabil
arXiv:2607.28146v1 Announce Type: new Abstract: As large language models (LLMs) are deployed as agents in high-stakes settings, such as medical and legal systems, understanding their deceptive capabilities is fundamental to safety. Controlled social deduction games provide a reproducible proxy for isolating and evaluating these complex adversarial behaviors. We present the open-source benchmark framework ParliamentBench based on the game Secret Hitler to evaluate LLMs in scenarios that require deception, persuasion, and reasoning under information asymmetry. We evaluate 16 LLMs across 1,600 simulated matches playing each other, playing against humans, and compare them against a large set of online games. We introduce three novel metrics that isolate social deduction, reasoning, and deceptive consistency. Our experiments reveal that frontier models achieve strong performance across cooperative and deceptive roles, with a strong top-four cluster (GPT-5.4, Kimi K2.5, Grok 4.1 Fast, and DeepSeek 3.1 Terminus), whereas the weakest models fall short of random (33%) and simple algorithmic (45%) baselines. Most LLMs struggle to maintain a consistent deceptive persona throughout an entire game, with deception retention dropping below 50%.
Related
- BOUNDARY_SYNC: Measuring Communication-Induced Representational Coupling in Multi-Agent LLM Systems
- Mind the Gap: Evaluating Model- and Agentic-Level Vulnerabilities in LLMs with Action Graphs
- Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows
Source: arXiv cs.CL | 2026-07-31