LLMs as Strategic Actors: Behavioral Alignment, Risk Calibration, and Argumentation Framing in Geopolitical Simulations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917306101137408 |
|---|---|
| author | Solopova, Veronika Skorik, Viktoria Tereshchenko, Maksym Haidun, Alina Vykhopen, Ostap |
| author_facet | Solopova, Veronika Skorik, Viktoria Tereshchenko, Maksym Haidun, Alina Vykhopen, Ostap |
| contents | Large language models (LLMs) are increasingly proposed as agents in strategic decision environments, yet their behavior in structured geopolitical simulations remains under-researched. We evaluate six popular state-of-the-art LLMs alongside results from human results across four real-world crisis simulation scenarios, requiring models to select predefined actions and justify their decisions across multiple rounds. We compare models to humans in action alignment, risk calibration through chosen actions' severity, and argumentative framing grounded in international relations theory. Results show that models approximate human decision patterns in base simulation rounds but diverge over time, displaying distinct behavioural profiles and strategy updates. LLM explanations for chosen actions across all models exhibit a strong normative-cooperative framing centered on stability, coordination, and risk mitigation, with limited adversarial reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_02128 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LLMs as Strategic Actors: Behavioral Alignment, Risk Calibration, and Argumentation Framing in Geopolitical Simulations Solopova, Veronika Skorik, Viktoria Tereshchenko, Maksym Haidun, Alina Vykhopen, Ostap Computation and Language Artificial Intelligence Computers and Society Large language models (LLMs) are increasingly proposed as agents in strategic decision environments, yet their behavior in structured geopolitical simulations remains under-researched. We evaluate six popular state-of-the-art LLMs alongside results from human results across four real-world crisis simulation scenarios, requiring models to select predefined actions and justify their decisions across multiple rounds. We compare models to humans in action alignment, risk calibration through chosen actions' severity, and argumentative framing grounded in international relations theory. Results show that models approximate human decision patterns in base simulation rounds but diverge over time, displaying distinct behavioural profiles and strategy updates. LLM explanations for chosen actions across all models exhibit a strong normative-cooperative framing centered on stability, coordination, and risk mitigation, with limited adversarial reasoning. |
| title | LLMs as Strategic Actors: Behavioral Alignment, Risk Calibration, and Argumentation Framing in Geopolitical Simulations |
| topic | Computation and Language Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2603.02128 |