Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents

Jul 17, 2026

Researchers introduce a multi-agent framework that combines Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Retrieval-Augmented Generation (RAG) to simulate political coalition negotiations using large language models. Applied to the 2019 Flemish election, the system produces stable coalition rankings and uses a novel tracing method to link agreement clauses back to party manifestos. The framework also benchmarks simulated agreements against real-world outcomes, offering a transparent and interpretable approach to studying party compatibility.

Why it matters: This work provides a transparent and scalable method for simulating and auditing political negotiations with LLMs, potentially advancing computational political science research.

Full story at: arXiv Computation and Language ↗