Search papers, labs, and topics across Lattice.
This paper investigates the strategic capabilities of LLMs by embedding them as players in a repeated security dilemma game, manipulating factors like multipolarity, time horizons, and communication. The study finds that LLMs exhibit behaviors consistent with established international relations theory, such as increased conflict in multipolar scenarios, unraveling due to finite horizons, and conflict reduction through communication. By analyzing both actions and internal reasoning, the authors showcase LLMs as a viable platform for exploring and validating strategic mechanisms.
LLMs playing international relations games reveal that they're not just regurgitating training data, but actually reasoning strategically like humans鈥攁nd even unraveling under pressure.
This paper asks whether large language models (LLMs) can be used to study the strategic foundations of conflict and cooperation. I introduce LLMs as experimental subjects in a repeated security dilemma and evaluate whether they reproduce canonical mechanisms from international relations theory. The baseline game is extended along three theoretically central dimensions: multipolarity, finite time horizons, and the availability of communication. Across multiple models, the results exhibit systematic and consistent patterns: multipolarity increases the likelihood of conflict, finite horizons induce universal unraveling consistent with backward-induction logic, and communication reduces conflict by enabling signaling and reciprocity. Beyond observed behavior, the design provides access to agents'private reasoning and public messages, allowing choices to be linked to underlying strategic logics such as preemption, cooperation under uncertainty, and trust-building. The contribution is primarily methodological. LLM-based experiments offer a scalable, transparent, and replicable approach to probing theoretical mechanisms.
