Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note2 min read

Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents

Source

arXiv

arxiv.org/abs/2607.15095v1

Read the source

Source

Plain-Language Brief

Researchers present a multi-agent framework using Large Language Models (LLMs) to simulate and audit political coalition formation in elections. The framework combines Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Retrieval-Augmented Generation (RAG) to create partisan agents that adhere to their official manifestos while maintaining ideological alignment. The study uses this framework on the 2019 Flemish election, demonstrating a stable winner and ranking, and accurately predicting which party's ideas were incorporated into the final agreement.

What the Document Says

  • Researchers present a multi-agent framework for simulating political coalition formation using LLMs.
  • The framework combines SFT, DPO, and RAG to create partisan agents adhering to their manifestos while maintaining ideological alignment.
  • The study uses the framework on the 2019 Flemish election, yielding a stable winner and ranking (N-VA ahead of CD&V and Open Vld).
  • Manifesto-anchored lineage reliably predicts real-world materialization in the final agreement.
  • The study demonstrates that hallucinated content does not accurately predict the final agreement.

Key Concepts Mentioned

  • Large Language Models (LLMs)
  • Supervised Fine-Tuning (SFT)
  • Direct Preference Optimization (DPO)
  • Retrieval-Augmented Generation (RAG)
  • Political coalition formation
  • 2019 Flemish election
  • manifesto-anchored lineage
  • Coalition Influence Score (CIS)

Claims Made by the Document

  • The presented framework can simulate political coalition formation accurately.
  • Manifesto-anchored lineage can reliably predict real-world materialization in the final agreement.

Evidence Used

  • The stable winner and ranking shown in the study
  • The accurate prediction of which party's ideas were incorporated into the final agreement

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

The formation of political coalitions is a complex negotiation driven by both concrete policy objectives and deep-seated ideological convictions. While Large Language Models (LLMs) open new avenues for computational political science, the neutrality and helpfulness biases instilled by Reinforcement Learning from Human Feedback (RLHF) prevent them from sustaining steadfast partisan behaviour. We present a multi-agent framework that reconciles factual grounding with ideological alignment by combining Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Retrieval-Augmented Generation (RAG): DPO instils aggressive party-specific personas, while a per-party RAG pipeline keeps each agent bounded to its official manifesto. We operationalize the framework on the 2019 Flemish election, deploying the partisan agents in a hub-and-spoke negotiation arbitrated by a formateur. To make the emergent negotiation interpretable, we introduce a Multi-Layered Information Lineage Topology (MILT) that traces every clause in the final agreement back to its manifesto origin and classifies it into five provenance states, a Coalition Influence Score (CIS) that aggregates these traceable contributions to identify which party shaped the agreement, and a real-world grounding pass that benchmarks each simulated provision against the historically adopted coalition agreement. Across three independent simulations the framework yields a stable winner and ranking (N-VA ahead of CD&V and Open Vld), and manifesto-anchored lineage reliably predicts real-world materialization whereas hallucinated content does not. The result is a transparent, scalable testbed for the ex-ante exploration of party compatibility and formateur-mediated compromise.