Frozen LLMs, using only retrieval over past communications and self-reflection rather than fine-tuning, can play the social deduction game Werewolf competently and show emergent strategic behavior, including deception, without being explicitly trained for it.

Capability: Strategic deception and detecting it · Behavior, Agentic

Observed on

2023, GPT-3.5/GPT-4 class. Autonomous agent.

Sources

supportsExploring Large Language Models for Communication Games: An Empirical Study on Werewolf
A tuning-free framework using retrieval and reflection on past communications let frozen LLMs play Werewolf competently, with emergent strategic behavior.

Status: activeLast checked: 2026-09-04Evidence activity

Contest this claim

Disagreeing is the most useful thing you can do here. Both sides of every contested claim in this catalog were assembled by the same person, which is its weakest point.

Related claims

State-of-the-art models such as GPT-4 can understand and induce false beliefs in other agents through deliberate strategic reasoning, a capability that was absent in earlier-generation language models.Strategic deception and detecting it